2025-11-07 12:40:17.507214: 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`.
2025-11-07 12:40:17.518351: 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 00:00:1762515617.531668 2696240 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762515617.535779 2696240 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762515617.545667 2696240 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762515617.545686 2696240 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762515617.545688 2696240 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762515617.545690 2696240 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 12:40:17.548673: 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(
2025-11-07 12:40:20,573	INFO worker.py:1927 -- Started a local Ray instance.
2025-11-07 12:40:21,246	INFO tune.py:253 -- Initializing Ray automatically. For cluster usage or custom Ray initialization, call `ray.init(...)` before `Tuner(...)`.
2025-11-07 12:40:21,313	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_a78d because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,317	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_78ad because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,322	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_ffa1 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,324	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_28d7 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,326	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_ce38 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,329	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_f7df because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,331	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_c97d because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,333	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_30a6 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,335	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_0d98 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,340	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_f25f because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,343	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_25eb because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,346	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_c7a9 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,349	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_7a46 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,352	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_d5c5 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,356	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_05b8 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,359	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_b434 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,367	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_5c04 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,371	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_3740 because trial dirname 'dir_8aa9a' already exists.
2025-11-07 12:40:21,380	INFO trial.py:182 -- Creating a new dirname dir_8aa9a_d3f0 because trial dirname 'dir_8aa9a' 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_M/case_M_CAPTURE24_acc_17_classes/CAPTURE24_hyperparameters_tuning
To visualize your results with TensorBoard, run: `tensorboard --logdir /tmp/ray/session_2025-11-07_12-40-19_849619_2696240/artifacts/2025-11-07_12-40-21/CAPTURE24_hyperparameters_tuning/driver_artifacts`

Trial status: 20 PENDING
Current time: 2025-11-07 12:40:21. Total running time: 0s
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 │
├─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ trial_8aa9a    PENDING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    PENDING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    PENDING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    PENDING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    PENDING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    PENDING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    PENDING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    PENDING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    PENDING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    PENDING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    PENDING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    PENDING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    PENDING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    PENDING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    PENDING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    PENDING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    PENDING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    PENDING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    PENDING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    PENDING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            27 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00011 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            27 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00004 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            27 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00004 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            23 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00007 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            24 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00012 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            16 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00005 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            29 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00019 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            28 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            28 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje              0.0001 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            17 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
[36m(train_cnn_ray_tune pid=2697828)[0m 2025-11-07 12:40:24.476601: 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`.
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            29 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    16 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            27 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00007 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            18 │
│ funcion_activacion              tanh │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     5 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00005 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            28 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00006 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            27 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00001 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            20 │
│ funcion_activacion              relu │
│ num_resblocks                      0 │
│ numero_filtros                    16 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00014 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            26 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00002 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            25 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00007 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            2 │
│ epochs                            27 │
│ funcion_activacion              tanh │
│ num_resblocks                      1 │
│ numero_filtros                    64 │
│ optimizador                     adam │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  32 │
│ tasa_aprendizaje             0.00005 │
╰──────────────────────────────────────╯
Trial trial_8aa9a started with configuration:
[36m(train_cnn_ray_tune pid=2697828)[0m 2025-11-07 12:40:24.500316: 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=2697828)[0m WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
[36m(train_cnn_ray_tune pid=2697828)[0m E0000 00:00:1762515624.534265 2698992 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=2697828)[0m E0000 00:00:1762515624.542935 2698992 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=2697828)[0m W0000 00:00:1762515624.563541 2698992 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=2697828)[0m W0000 00:00:1762515624.563602 2698992 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=2697828)[0m W0000 00:00:1762515624.563605 2698992 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=2697828)[0m W0000 00:00:1762515624.563607 2698992 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=2697828)[0m 2025-11-07 12:40:24.570011: 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=2697828)[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=2697828)[0m 2025-11-07 12:40:27.607137: 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=2697828)[0m 2025-11-07 12:40:27.607187: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:167] env: CUDA_VISIBLE_DEVICES=""
[36m(train_cnn_ray_tune pid=2697828)[0m 2025-11-07 12:40:27.607197: 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=2697828)[0m 2025-11-07 12:40:27.607203: 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=2697828)[0m 2025-11-07 12:40:27.607208: 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=2697828)[0m 2025-11-07 12:40:27.607212: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:190] hostname: simur-MS-7B94
[36m(train_cnn_ray_tune pid=2697828)[0m 2025-11-07 12:40:27.607425: 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=2697828)[0m 2025-11-07 12:40:27.607459: 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=2697828)[0m 2025-11-07 12:40:27.607464: I external/local_xla/xla/stream_executor/cuda/cuda_diagnostics.cc:291] kernel version seems to match DSO: 570.133.7
╭──────────────────────────────────────╮
│ Trial trial_8aa9a config             │
├──────────────────────────────────────┤
│ N_capas                            3 │
│ epochs                            16 │
│ funcion_activacion              relu │
│ num_resblocks                      1 │
│ numero_filtros                    32 │
│ optimizador                  rmsprop │
│ tamanho_filtro                     3 │
│ tamanho_minilote                  16 │
│ tasa_aprendizaje             0.00004 │
╰──────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697828)[0m Epoch 1/27
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59:18[0m 3s/step - accuracy: 0.0000e+00 - loss: 3.5474
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.0174 - loss: 3.6123    
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.0271 - loss: 3.5435
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57:25[0m 3s/step - accuracy: 0.0625 - loss: 3.6291
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.0625 - loss: 3.4894
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0742 - loss: 3.3088
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.0336 - loss: 3.5215
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.0367 - loss: 3.5145
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.0652 - loss: 3.4037
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 31ms/step - accuracy: 0.0142 - loss: 3.5444
[1m  8/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.0204 - loss: 3.5626
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 11/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.0267 - loss: 3.5441
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 13/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.0305 - loss: 3.5307
[1m 16/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.0344 - loss: 3.5116
[36m(train_cnn_ray_tune pid=2697835)[0m Epoch 1/16[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=2697828)[0m 
[1m 18/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 27ms/step - accuracy: 0.0368 - loss: 3.4998
[1m 20/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.0393 - loss: 3.4869
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 22/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.0416 - loss: 3.4758
[1m 24/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 27ms/step - accuracy: 0.0434 - loss: 3.4675
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.0156 - loss: 3.6085     
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.1562 - loss: 3.0606  
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 57ms/step - accuracy: 0.1597 - loss: 3.0679
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 26/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.0453 - loss: 3.4597
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 47ms/step - accuracy: 0.0482 - loss: 3.4234 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 43ms/step - accuracy: 0.0606 - loss: 3.3518
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 45ms/step - accuracy: 0.1596 - loss: 3.0671 
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 28/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.0470 - loss: 3.4522
[1m 30/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.0486 - loss: 3.4446
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 32/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 29ms/step - accuracy: 0.0502 - loss: 3.4380
[1m 35/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.0525 - loss: 3.4284
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 44ms/step - accuracy: 0.1007 - loss: 3.2724  
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 37/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 29ms/step - accuracy: 0.0539 - loss: 3.4224
[1m 39/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 29ms/step - accuracy: 0.0554 - loss: 3.4158
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 34ms/step - accuracy: 0.0243 - loss: 3.6217      
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.0421 - loss: 3.5237
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 27ms/step - accuracy: 0.0463 - loss: 3.5450
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 27ms/step - accuracy: 0.0465 - loss: 3.5435
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 27ms/step - accuracy: 0.0467 - loss: 3.5419
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.0430 - loss: 3.4031
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.0444 - loss: 3.3835
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.0816 - loss: 3.3474  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 43ms/step - accuracy: 0.0768 - loss: 3.3473
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.0491 - loss: 3.3594
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.0523 - loss: 3.3537
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.0565 - loss: 3.3478
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:56[0m 101ms/step - accuracy: 0.0312 - loss: 3.3958    
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:34[0m 82ms/step - accuracy: 0.0347 - loss: 3.3640 
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:22:51[0m 7s/step - accuracy: 0.0000e+00 - loss: 3.4639[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.0081 - loss: 3.2928    
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.0139 - loss: 3.2820
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:25:22[0m 4s/step - accuracy: 0.1250 - loss: 3.8486
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 83ms/step - accuracy: 0.1094 - loss: 3.7224 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 53ms/step - accuracy: 0.1014 - loss: 3.2403[32m [repeated 199x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 40ms/step - accuracy: 0.0719 - loss: 3.3631
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 40ms/step - accuracy: 0.0718 - loss: 3.3634[32m [repeated 207x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 23/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 67ms/step - accuracy: 0.0720 - loss: 3.3224
[1m 24/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 67ms/step - accuracy: 0.0715 - loss: 3.3237[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 34/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 56ms/step - accuracy: 0.0731 - loss: 3.2903[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:37[0m 84ms/step - accuracy: 0.0312 - loss: 3.4436     
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.0715 - loss: 3.3496 
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.0717 - loss: 3.3513[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  41/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 70ms/step - accuracy: 0.0762 - loss: 3.5889[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:39[0m 86ms/step - accuracy: 0.2031 - loss: 3.7020 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 54ms/step - accuracy: 0.0725 - loss: 3.3587
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 54ms/step - accuracy: 0.0726 - loss: 3.3581
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 54ms/step - accuracy: 0.0726 - loss: 3.3573[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 70ms/step - accuracy: 0.0695 - loss: 3.4782
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 70ms/step - accuracy: 0.0695 - loss: 3.4758[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 31ms/step - accuracy: 0.0939 - loss: 3.1019[32m [repeated 319x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 201/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m43s[0m 46ms/step - accuracy: 0.0672 - loss: 3.3769
[1m 202/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m43s[0m 46ms/step - accuracy: 0.0672 - loss: 3.3769[32m [repeated 253x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m113/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 59ms/step - accuracy: 0.0831 - loss: 3.2225
[1m114/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 59ms/step - accuracy: 0.0832 - loss: 3.2216[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m115/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 59ms/step - accuracy: 0.0834 - loss: 3.2208[32m [repeated 184x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 70ms/step - accuracy: 0.0711 - loss: 3.4174[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m305/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1090 - loss: 3.1366
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m307/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1091 - loss: 3.1356
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m309/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1093 - loss: 3.1346
[1m311/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1094 - loss: 3.1336
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m139/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m25s[0m 58ms/step - accuracy: 0.0866 - loss: 3.2021
[1m140/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m25s[0m 58ms/step - accuracy: 0.0867 - loss: 3.2013
[1m141/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m25s[0m 58ms/step - accuracy: 0.0868 - loss: 3.2006
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m43s[0m 45ms/step - accuracy: 0.0675 - loss: 3.3767
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m43s[0m 45ms/step - accuracy: 0.0674 - loss: 3.3768
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m43s[0m 45ms/step - accuracy: 0.0674 - loss: 3.3768[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 147/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 65ms/step - accuracy: 0.0960 - loss: 3.1465
[1m 148/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 65ms/step - accuracy: 0.0962 - loss: 3.1454[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m24s[0m 34ms/step - accuracy: 0.0733 - loss: 3.3876[32m [repeated 304x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m23s[0m 32ms/step - accuracy: 0.1012 - loss: 3.0534
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m23s[0m 32ms/step - accuracy: 0.1013 - loss: 3.0529[32m [repeated 266x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m205/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 57ms/step - accuracy: 0.0939 - loss: 3.1612
[1m206/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m21s[0m 57ms/step - accuracy: 0.0940 - loss: 3.1607[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m249/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m15s[0m 48ms/step - accuracy: 0.0913 - loss: 3.1940[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 67ms/step - accuracy: 0.0793 - loss: 3.3106[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m435/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 37ms/step - accuracy: 0.1170 - loss: 3.0805[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m437/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 37ms/step - accuracy: 0.1171 - loss: 3.0797
[1m439/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 37ms/step - accuracy: 0.1173 - loss: 3.0790[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m222/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 57ms/step - accuracy: 0.0956 - loss: 3.1519
[1m223/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 57ms/step - accuracy: 0.0957 - loss: 3.1514
[1m224/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m20s[0m 57ms/step - accuracy: 0.0958 - loss: 3.1508[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m36s[0m 44ms/step - accuracy: 0.0662 - loss: 3.3421
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m36s[0m 44ms/step - accuracy: 0.0662 - loss: 3.3420
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m36s[0m 44ms/step - accuracy: 0.0662 - loss: 3.3418[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 64ms/step - accuracy: 0.1102 - loss: 3.0805 
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 64ms/step - accuracy: 0.1103 - loss: 3.0798
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 66ms/step - accuracy: 0.0841 - loss: 3.2700
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 66ms/step - accuracy: 0.0842 - loss: 3.2691[32m [repeated 35x across cluster][0m

Trial status: 20 RUNNING
Current time: 2025-11-07 12:40:51. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m59s[0m 66ms/step - accuracy: 0.0865 - loss: 3.2527[32m [repeated 330x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m36s[0m 48ms/step - accuracy: 0.0650 - loss: 3.3789
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m36s[0m 48ms/step - accuracy: 0.0650 - loss: 3.3789[32m [repeated 251x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m292/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 57ms/step - accuracy: 0.1021 - loss: 3.1183
[1m293/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 57ms/step - accuracy: 0.1022 - loss: 3.1179[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m294/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 57ms/step - accuracy: 0.1023 - loss: 3.1175[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 66ms/step - accuracy: 0.0853 - loss: 3.2607[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m410/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 47ms/step - accuracy: 0.1153 - loss: 3.0647[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m553/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.1095 - loss: 3.0276
[1m555/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.1096 - loss: 3.0271[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m372/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.0963 - loss: 3.1640 
[1m373/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.0963 - loss: 3.1637
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m36s[0m 49ms/step - accuracy: 0.0896 - loss: 3.1888
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m36s[0m 49ms/step - accuracy: 0.0897 - loss: 3.1884
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m36s[0m 49ms/step - accuracy: 0.0897 - loss: 3.1881[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:00[0m 66ms/step - accuracy: 0.0857 - loss: 3.2583
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m59s[0m 66ms/step - accuracy: 0.0858 - loss: 3.2575 [32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 32ms/step - accuracy: 0.1117 - loss: 2.9872[32m [repeated 413x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m54s[0m 66ms/step - accuracy: 0.0941 - loss: 3.2013
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m54s[0m 66ms/step - accuracy: 0.0942 - loss: 3.2007[32m [repeated 285x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m375/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.1083 - loss: 3.0874
[1m376/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.1084 - loss: 3.0871
[1m377/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.1084 - loss: 3.0868
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m370/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 58ms/step - accuracy: 0.1080 - loss: 3.0891
[1m372/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.1081 - loss: 3.0884[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m381/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 57ms/step - accuracy: 0.1087 - loss: 3.0854[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 42ms/step - accuracy: 0.1105 - loss: 3.0206 - val_accuracy: 0.2049 - val_loss: 2.4367
[36m(train_cnn_ray_tune pid=2697881)[0m Epoch 2/20
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 93ms/step - accuracy: 0.1250 - loss: 2.6011
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1018 - loss: 3.1574
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1018 - loss: 3.1570
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1019 - loss: 3.1567
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1019 - loss: 3.1564
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1019 - loss: 3.1561
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1020 - loss: 3.1558
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1020 - loss: 3.1555
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1021 - loss: 3.1552
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m471/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.0990 - loss: 3.1444[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m473/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.0991 - loss: 3.1440
[1m475/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 48ms/step - accuracy: 0.0991 - loss: 3.1437[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 113ms/step - accuracy: 0.0938 - loss: 2.6849
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 59ms/step - accuracy: 0.0938 - loss: 2.6253  
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1021 - loss: 3.1549
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1021 - loss: 3.1547
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1021 - loss: 3.1545
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1022 - loss: 3.1542
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1022 - loss: 3.1539
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1023 - loss: 3.1536
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1023 - loss: 3.1533
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1023 - loss: 3.1530
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1024 - loss: 3.1527
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m404/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1102 - loss: 3.0780 
[1m406/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 57ms/step - accuracy: 0.1103 - loss: 3.0774
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1024 - loss: 3.1524
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1024 - loss: 3.1521
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m29s[0m 48ms/step - accuracy: 0.0656 - loss: 3.3728
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m29s[0m 48ms/step - accuracy: 0.0656 - loss: 3.3727
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m29s[0m 48ms/step - accuracy: 0.0656 - loss: 3.3726[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1025 - loss: 3.1519
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1025 - loss: 3.1516
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1025 - loss: 3.1513
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1026 - loss: 3.1510
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1026 - loss: 3.1507
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1027 - loss: 3.1504
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1027 - loss: 3.1501
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1027 - loss: 3.1497
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1028 - loss: 3.1494
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1028 - loss: 3.1491
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1029 - loss: 3.1488
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.1029 - loss: 3.1486
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1029 - loss: 3.1483
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1030 - loss: 3.1480
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1030 - loss: 3.1477
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1030 - loss: 3.1474
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1031 - loss: 3.1471
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1031 - loss: 3.1469
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1032 - loss: 3.1464
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1032 - loss: 3.1462
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1032 - loss: 3.1459
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1033 - loss: 3.1456
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1033 - loss: 3.1453
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1033 - loss: 3.1450
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1034 - loss: 3.1448
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1034 - loss: 3.1445
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1034 - loss: 3.1442
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1035 - loss: 3.1439
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1035 - loss: 3.1437
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1036 - loss: 3.1434
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1036 - loss: 3.1431
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1036 - loss: 3.1428
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1037 - loss: 3.1424
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1037 - loss: 3.1421
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1037 - loss: 3.1419
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1038 - loss: 3.1415
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1038 - loss: 3.1411
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1039 - loss: 3.1408
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1039 - loss: 3.1405
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1040 - loss: 3.1402
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1040 - loss: 3.1398
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.1040 - loss: 3.1396
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.1041 - loss: 3.1393
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1147 - loss: 2.9660 
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1147 - loss: 2.9657
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.1041 - loss: 3.1390
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.1041 - loss: 3.1388
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m49s[0m 66ms/step - accuracy: 0.1003 - loss: 3.1601[32m [repeated 360x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m26s[0m 49ms/step - accuracy: 0.0658 - loss: 3.3698
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m26s[0m 49ms/step - accuracy: 0.0658 - loss: 3.3697[32m [repeated 271x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m123/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m17s[0m 39ms/step - accuracy: 0.1666 - loss: 2.6550
[1m124/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m17s[0m 39ms/step - accuracy: 0.1666 - loss: 2.6551[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m121/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m17s[0m 39ms/step - accuracy: 0.1667 - loss: 2.6549[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 45ms/step - accuracy: 0.1229 - loss: 3.0344 - val_accuracy: 0.2132 - val_loss: 2.3985
[36m(train_cnn_ray_tune pid=2697828)[0m Epoch 2/27
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.0872 - loss: 3.2878
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.0873 - loss: 3.2874[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m482/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 57ms/step - accuracy: 0.1145 - loss: 3.0556[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 57ms/step - accuracy: 0.1143 - loss: 3.0567
[1m479/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 57ms/step - accuracy: 0.1143 - loss: 3.0564[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 31ms/step - accuracy: 0.1051 - loss: 3.1309[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 54ms/step - accuracy: 0.1239 - loss: 3.0118 - val_accuracy: 0.2182 - val_loss: 2.3711
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 2/27
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 107ms/step - accuracy: 0.1875 - loss: 2.5593
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m34s[0m 60ms/step - accuracy: 0.1244 - loss: 3.0360[32m [repeated 330x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m43s[0m 66ms/step - accuracy: 0.1049 - loss: 3.1265
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m43s[0m 66ms/step - accuracy: 0.1050 - loss: 3.1261[32m [repeated 226x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m269/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.1638 - loss: 2.6461
[1m271/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.1638 - loss: 2.6459[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 53/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 46ms/step - accuracy: 0.1766 - loss: 2.6663[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 33ms/step - accuracy: 0.1181 - loss: 2.9405
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 33ms/step - accuracy: 0.1182 - loss: 2.9401[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m570/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 57ms/step - accuracy: 0.1184 - loss: 3.0343[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 57ms/step - accuracy: 0.0868 - loss: 2.9725  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 57ms/step - accuracy: 0.0866 - loss: 2.9908
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m561/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 57ms/step - accuracy: 0.1181 - loss: 3.0363
[1m562/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 57ms/step - accuracy: 0.1181 - loss: 3.0361[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 33ms/step - accuracy: 0.1185 - loss: 2.9379[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.1380 - loss: 2.9332 
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.1381 - loss: 2.9328
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 63ms/step - accuracy: 0.0721 - loss: 3.3571 - val_accuracy: 0.1185 - val_loss: 2.9213[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 2/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 123ms/step - accuracy: 0.0938 - loss: 3.2350[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 35ms/step - accuracy: 0.0922 - loss: 3.2534
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 36ms/step - accuracy: 0.0922 - loss: 3.2532
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 35ms/step - accuracy: 0.0922 - loss: 3.2529
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.0731 - loss: 3.2741
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.0732 - loss: 3.2739
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.0732 - loss: 3.2737
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m38s[0m 65ms/step - accuracy: 0.1091 - loss: 3.0965[32m [repeated 297x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 44ms/step - accuracy: 0.0735 - loss: 3.2711
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 44ms/step - accuracy: 0.0735 - loss: 3.2709[32m [repeated 208x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 49/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 53ms/step - accuracy: 0.0992 - loss: 3.2184
[1m 50/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 53ms/step - accuracy: 0.0993 - loss: 3.2181
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 53ms/step - accuracy: 0.0995 - loss: 3.2179
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m338/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1581 - loss: 2.6633 
[1m339/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1581 - loss: 2.6632
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 56/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 53ms/step - accuracy: 0.1001 - loss: 3.2168
[1m 57/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 54ms/step - accuracy: 0.1002 - loss: 3.2166[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m172/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 45ms/step - accuracy: 0.1765 - loss: 2.6709[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.0946 - loss: 3.2231
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.0946 - loss: 3.2230[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m359/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1588 - loss: 2.6615[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m442/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 36ms/step - accuracy: 0.1653 - loss: 2.6308
[1m444/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 36ms/step - accuracy: 0.1653 - loss: 2.6307[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 42ms/step - accuracy: 0.0949 - loss: 3.2209[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m45s[0m 36ms/step - accuracy: 0.1071 - loss: 3.1154 - val_accuracy: 0.2089 - val_loss: 2.4608
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.0941 - loss: 3.2260 
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.0941 - loss: 3.2257
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:41[0m 88ms/step - accuracy: 0.0625 - loss: 2.9674
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.0833 - loss: 2.8593 
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.0740 - loss: 3.2665 
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.0740 - loss: 3.2663
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 59ms/step - accuracy: 0.1875 - loss: 2.7089  
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 55ms/step - accuracy: 0.1771 - loss: 2.7727
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m45s[0m 66ms/step - accuracy: 0.1188 - loss: 3.0323 - val_accuracy: 0.2476 - val_loss: 2.3648
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 2/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 130ms/step - accuracy: 0.2188 - loss: 2.6354
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 42ms/step - accuracy: 0.0959 - loss: 3.2145
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 42ms/step - accuracy: 0.0960 - loss: 3.2144
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 42ms/step - accuracy: 0.0960 - loss: 3.2142
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m17s[0m 50ms/step - accuracy: 0.1050 - loss: 3.0911
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m17s[0m 50ms/step - accuracy: 0.1050 - loss: 3.0910
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m17s[0m 50ms/step - accuracy: 0.1050 - loss: 3.0908
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m32s[0m 65ms/step - accuracy: 0.1131 - loss: 3.0695[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m31s[0m 63ms/step - accuracy: 0.1472 - loss: 2.9037
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m31s[0m 63ms/step - accuracy: 0.1473 - loss: 2.9034[32m [repeated 193x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 46/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 57ms/step - accuracy: 0.1604 - loss: 2.7642
[1m 47/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 57ms/step - accuracy: 0.1605 - loss: 2.7634
[1m 48/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 57ms/step - accuracy: 0.1606 - loss: 2.7627
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m151/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 53ms/step - accuracy: 0.1048 - loss: 3.1892
[1m152/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 54ms/step - accuracy: 0.1048 - loss: 3.1889[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m154/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 53ms/step - accuracy: 0.1049 - loss: 3.1884[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 45ms/step - accuracy: 0.1221 - loss: 2.9791
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 45ms/step - accuracy: 0.1222 - loss: 2.9789[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m492/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 41ms/step - accuracy: 0.1623 - loss: 2.6520[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m493/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 41ms/step - accuracy: 0.1623 - loss: 2.6520
[1m495/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 41ms/step - accuracy: 0.1623 - loss: 2.6518[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:42[0m 140ms/step - accuracy: 0.3125 - loss: 2.2294
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 45ms/step - accuracy: 0.1224 - loss: 2.9773[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 44ms/step - accuracy: 0.2292 - loss: 2.4646  
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 33ms/step - accuracy: 0.2104 - loss: 2.4732
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m50s[0m 39ms/step - accuracy: 0.1202 - loss: 2.9256 - val_accuracy: 0.2148 - val_loss: 2.3714
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 60ms/step - accuracy: 0.1289 - loss: 3.0000
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 60ms/step - accuracy: 0.1289 - loss: 2.9999
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 60ms/step - accuracy: 0.1289 - loss: 2.9997
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m50s[0m 41ms/step - accuracy: 0.0934 - loss: 3.2445 - val_accuracy: 0.2140 - val_loss: 2.4732
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.2500 - loss: 2.8671
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.2370 - loss: 2.8852 
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 2/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.0881 - loss: 3.2199 
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.0881 - loss: 3.2196
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m350/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.1744 - loss: 2.6718 
[1m351/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.1744 - loss: 2.6718
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.1665 - loss: 2.6224 - val_accuracy: 0.2521 - val_loss: 2.3171
Trial status: 20 RUNNING
Current time: 2025-11-07 12:41:21. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m369/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.1744 - loss: 2.6714
[1m370/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.1744 - loss: 2.6714
[1m371/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.1744 - loss: 2.6713
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 34ms/step - accuracy: 0.1727 - loss: 2.6172[32m [repeated 243x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m27s[0m 64ms/step - accuracy: 0.1167 - loss: 3.0454
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m27s[0m 64ms/step - accuracy: 0.1168 - loss: 3.0451[32m [repeated 172x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m160/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 55ms/step - accuracy: 0.1620 - loss: 2.7382
[1m162/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 55ms/step - accuracy: 0.1620 - loss: 2.7379[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m164/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 55ms/step - accuracy: 0.1620 - loss: 2.7377[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 50ms/step - accuracy: 0.0670 - loss: 3.3515
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 50ms/step - accuracy: 0.0670 - loss: 3.3515[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m412/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 44ms/step - accuracy: 0.1744 - loss: 2.6706[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m414/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 44ms/step - accuracy: 0.1744 - loss: 2.6705
[1m416/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 44ms/step - accuracy: 0.1744 - loss: 2.6705[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:36[0m 167ms/step - accuracy: 0.1562 - loss: 2.6113[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 50ms/step - accuracy: 0.0670 - loss: 3.3510[32m [repeated 143x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m24s[0m 63ms/step - accuracy: 0.1524 - loss: 2.8741
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m24s[0m 63ms/step - accuracy: 0.1525 - loss: 2.8738
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m23s[0m 63ms/step - accuracy: 0.1525 - loss: 2.8736
[36m(train_cnn_ray_tune pid=2697881)[0m Epoch 3/20
[36m(train_cnn_ray_tune pid=2697828)[0m Epoch 3/27
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 47ms/step - accuracy: 0.1638 - loss: 2.6465 - val_accuracy: 0.2323 - val_loss: 2.3332
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m21s[0m 64ms/step - accuracy: 0.1198 - loss: 3.0243[32m [repeated 183x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 284/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 31ms/step - accuracy: 0.1658 - loss: 2.6173
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m26s[0m 31ms/step - accuracy: 0.1658 - loss: 2.6173[32m [repeated 151x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m256/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.1641 - loss: 2.7274
[1m258/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.1642 - loss: 2.7271[32m [repeated 89x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m259/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.1642 - loss: 2.7270[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 52ms/step - accuracy: 0.1042 - loss: 3.1467
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 52ms/step - accuracy: 0.1043 - loss: 3.1464[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m60s[0m 47ms/step - accuracy: 0.0992 - loss: 3.1946 - val_accuracy: 0.2188 - val_loss: 2.5028
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1354 - loss: 2.7064 
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m536/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 44ms/step - accuracy: 0.1742 - loss: 2.6669[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1445 - loss: 2.7100
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1506 - loss: 2.6978
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m444/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 46ms/step - accuracy: 0.1257 - loss: 2.8602
[1m446/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 46ms/step - accuracy: 0.1258 - loss: 2.8600[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:57[0m 102ms/step - accuracy: 0.1250 - loss: 2.5595[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1550 - loss: 2.7076
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1622 - loss: 2.7211 
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 49ms/step - accuracy: 0.0674 - loss: 3.3464[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 31ms/step - accuracy: 0.1434 - loss: 2.7931
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 31ms/step - accuracy: 0.1434 - loss: 2.7931
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 31ms/step - accuracy: 0.1435 - loss: 2.7931
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m276/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1895 - loss: 2.4961 
[1m278/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.1895 - loss: 2.4961
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.2188 - loss: 2.2991  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.2206 - loss: 2.3721
[36m(train_cnn_ray_tune pid=2697873)[0m Epoch 2/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 59ms/step - accuracy: 0.1336 - loss: 2.9652
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 59ms/step - accuracy: 0.1336 - loss: 2.9651
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 59ms/step - accuracy: 0.1336 - loss: 2.9650
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m16s[0m 64ms/step - accuracy: 0.1226 - loss: 3.0059[32m [repeated 180x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m16s[0m 64ms/step - accuracy: 0.1226 - loss: 3.0057
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m16s[0m 64ms/step - accuracy: 0.1226 - loss: 3.0055[32m [repeated 176x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m353/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 53ms/step - accuracy: 0.1664 - loss: 2.7160
[1m355/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 53ms/step - accuracy: 0.1665 - loss: 2.7158[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m357/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 53ms/step - accuracy: 0.1665 - loss: 2.7156[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 49ms/step - accuracy: 0.1744 - loss: 2.6652 - val_accuracy: 0.2271 - val_loss: 2.3402
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 51ms/step - accuracy: 0.1072 - loss: 3.1288
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 51ms/step - accuracy: 0.1073 - loss: 3.1286[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m63s[0m 51ms/step - accuracy: 0.1248 - loss: 2.9627 - val_accuracy: 0.2335 - val_loss: 2.3590[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 41ms/step - accuracy: 0.0764 - loss: 3.1262  
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m403/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.1887 - loss: 2.4957[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m410/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.1887 - loss: 2.4956
[1m413/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.1887 - loss: 2.4956[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 102ms/step - accuracy: 0.1250 - loss: 2.6218[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m372/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 53ms/step - accuracy: 0.1668 - loss: 2.7142
[1m373/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 53ms/step - accuracy: 0.1668 - loss: 2.7141
[1m374/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 53ms/step - accuracy: 0.1669 - loss: 2.7140
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 59ms/step - accuracy: 0.1341 - loss: 2.9613[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m19s[0m 30ms/step - accuracy: 0.1658 - loss: 2.6118
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 30ms/step - accuracy: 0.1658 - loss: 2.6117
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 30ms/step - accuracy: 0.1658 - loss: 2.6117
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m472/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 52ms/step - accuracy: 0.1112 - loss: 3.1501
[1m473/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 52ms/step - accuracy: 0.1112 - loss: 3.1501
[1m474/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 52ms/step - accuracy: 0.1113 - loss: 3.1500
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m388/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.1103 - loss: 3.1566 
[1m389/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.1103 - loss: 3.1565
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 3/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:00[0m 157ms/step - accuracy: 0.1250 - loss: 3.0754
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1406 - loss: 2.9210 
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1285 - loss: 2.9402
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1321 - loss: 2.9472
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 49ms/step - accuracy: 0.1381 - loss: 2.9484 
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 44ms/step - accuracy: 0.0000e+00 - loss: 3.5372  
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.0082 - loss: 3.4800    
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m10s[0m 63ms/step - accuracy: 0.1254 - loss: 2.9872[32m [repeated 236x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 37ms/step - accuracy: 0.0362 - loss: 3.3381
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.0376 - loss: 3.3305[32m [repeated 180x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 41ms/step - accuracy: 0.0868 - loss: 3.0378  
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 20/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 58ms/step - accuracy: 0.1585 - loss: 2.7966
[1m 22/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 56ms/step - accuracy: 0.1578 - loss: 2.7948[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m108/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m20s[0m 44ms/step - accuracy: 0.1989 - loss: 2.5549[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1454 - loss: 2.7845 
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1454 - loss: 2.7844
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 49ms/step - accuracy: 0.1282 - loss: 2.8509 - val_accuracy: 0.2069 - val_loss: 2.3847
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 63ms/step - accuracy: 0.1257 - loss: 2.9851
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 63ms/step - accuracy: 0.1258 - loss: 2.9849[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m69s[0m 56ms/step - accuracy: 0.1141 - loss: 3.0314 - val_accuracy: 0.2335 - val_loss: 2.3760[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m559/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 52ms/step - accuracy: 0.1122 - loss: 3.1431[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m457/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 54ms/step - accuracy: 0.1685 - loss: 2.7068
[1m459/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 54ms/step - accuracy: 0.1686 - loss: 2.7067[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:00[0m 105ms/step - accuracy: 0.0625 - loss: 3.1106[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 61ms/step - accuracy: 0.1617 - loss: 2.8184[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 43ms/step - accuracy: 0.0530 - loss: 3.2685
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 43ms/step - accuracy: 0.0535 - loss: 3.2665
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 43ms/step - accuracy: 0.0544 - loss: 3.2631
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  98/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 46ms/step - accuracy: 0.1228 - loss: 3.0034
[1m  99/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 46ms/step - accuracy: 0.1228 - loss: 3.0034
[1m 100/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 46ms/step - accuracy: 0.1227 - loss: 3.0034
[36m(train_cnn_ray_tune pid=2697885)[0m Epoch 2/25[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 54ms/step - accuracy: 0.1496 - loss: 2.8718 [32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.1488 - loss: 2.8772
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.1490 - loss: 2.8762[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 91/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 49ms/step - accuracy: 0.1529 - loss: 2.7744
[1m 92/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 49ms/step - accuracy: 0.1529 - loss: 2.7741
[1m 93/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 49ms/step - accuracy: 0.1528 - loss: 2.7738
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 37ms/step - accuracy: 0.1889 - loss: 2.4929 - val_accuracy: 0.2587 - val_loss: 2.2616
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 91ms/step - accuracy: 0.2812 - loss: 2.2612
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 47ms/step - accuracy: 0.2448 - loss: 2.3466
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 31ms/step - accuracy: 0.1670 - loss: 2.6047[32m [repeated 235x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 35ms/step - accuracy: 0.1471 - loss: 2.9010
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 35ms/step - accuracy: 0.1471 - loss: 2.9009[32m [repeated 189x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m128/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 49ms/step - accuracy: 0.1512 - loss: 2.7696
[1m129/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 49ms/step - accuracy: 0.1512 - loss: 2.7696[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 35/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 33ms/step - accuracy: 0.1988 - loss: 2.4224[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 63ms/step - accuracy: 0.1257 - loss: 2.9855 
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 63ms/step - accuracy: 0.1257 - loss: 2.9853
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m3s[0m 61ms/step - accuracy: 0.1639 - loss: 2.8047
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 61ms/step - accuracy: 0.1639 - loss: 2.8044[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m74s[0m 58ms/step - accuracy: 0.1079 - loss: 3.1250 - val_accuracy: 0.2549 - val_loss: 2.3752
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m550/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 54ms/step - accuracy: 0.1700 - loss: 2.6993[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m552/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 54ms/step - accuracy: 0.1700 - loss: 2.6991
[1m554/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 54ms/step - accuracy: 0.1701 - loss: 2.6990[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 109ms/step - accuracy: 0.1875 - loss: 2.9327
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 61ms/step - accuracy: 0.1641 - loss: 2.8030[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1673 - loss: 2.6036 
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1673 - loss: 2.6036
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 30ms/step - accuracy: 0.1462 - loss: 2.7792
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 30ms/step - accuracy: 0.1462 - loss: 2.7791
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 30ms/step - accuracy: 0.1462 - loss: 2.7791
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m575/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 54ms/step - accuracy: 0.1703 - loss: 2.6974
[1m576/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 54ms/step - accuracy: 0.1704 - loss: 2.6973
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 54ms/step - accuracy: 0.1704 - loss: 2.6972
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m173/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 48ms/step - accuracy: 0.1502 - loss: 2.7668
[1m174/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 48ms/step - accuracy: 0.1502 - loss: 2.7667
[1m175/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 48ms/step - accuracy: 0.1502 - loss: 2.7666
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 47ms/step - accuracy: 0.0696 - loss: 3.2066
[1m 172/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 47ms/step - accuracy: 0.0697 - loss: 3.2065
[1m 173/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 47ms/step - accuracy: 0.0697 - loss: 3.2064
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 3/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 58ms/step - accuracy: 0.1125 - loss: 3.1415 - val_accuracy: 0.1531 - val_loss: 2.7428
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:29[0m 129ms/step - accuracy: 0.0625 - loss: 2.9137
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.0625 - loss: 2.9625  
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m27s[0m 40ms/step - accuracy: 0.2246 - loss: 2.4531[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m27s[0m 40ms/step - accuracy: 0.2245 - loss: 2.4532
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m27s[0m 39ms/step - accuracy: 0.2245 - loss: 2.4533[32m [repeated 208x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m250/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 45ms/step - accuracy: 0.1507 - loss: 2.7594
[1m253/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 45ms/step - accuracy: 0.1508 - loss: 2.7592[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 59ms/step - accuracy: 0.1704 - loss: 2.6971 - val_accuracy: 0.2349 - val_loss: 2.3014
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 90ms/step - accuracy: 0.2188 - loss: 2.5238
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 98/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 52ms/step - accuracy: 0.1405 - loss: 2.9804[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 31ms/step - accuracy: 0.1678 - loss: 2.6009
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 30ms/step - accuracy: 0.1678 - loss: 2.6008[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m359/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1920 - loss: 2.5514[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m361/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1919 - loss: 2.5514
[1m363/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1919 - loss: 2.5514[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1468 - loss: 2.8948[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m81s[0m 66ms/step - accuracy: 0.1360 - loss: 2.9465 - val_accuracy: 0.2382 - val_loss: 2.3707
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46[0m 93ms/step - accuracy: 0.2500 - loss: 2.2457
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.2188 - loss: 2.3452
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 63ms/step - accuracy: 0.2083 - loss: 2.3882
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1992 - loss: 2.4319
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1969 - loss: 2.4674
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.1988 - loss: 2.4961
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 51ms/step - accuracy: 0.1641 - loss: 2.4059  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 42ms/step - accuracy: 0.1647 - loss: 2.4505
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.2023 - loss: 2.5114
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.2048 - loss: 2.5352
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.2049 - loss: 2.5427
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  12/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.2052 - loss: 2.5548
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2033 - loss: 2.5646
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2017 - loss: 2.5694
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2001 - loss: 2.5735
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1985 - loss: 2.5774
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1975 - loss: 2.5808
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1961 - loss: 2.5837
[36m(train_cnn_ray_tune pid=2697828)[0m Epoch 4/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1937 - loss: 2.5897
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1924 - loss: 2.5921
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1912 - loss: 2.5941
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1902 - loss: 2.5956
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1882 - loss: 2.5986
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.1867 - loss: 2.6012 
Trial status: 20 RUNNING
Current time: 2025-11-07 12:41:51. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  40/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1833 - loss: 2.6097
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  42/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 54ms/step - accuracy: 0.1830 - loss: 2.6112 
[1m  44/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 54ms/step - accuracy: 0.1827 - loss: 2.6129
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m349/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.1512 - loss: 2.7533
[1m350/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.1512 - loss: 2.7533
[1m352/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.1512 - loss: 2.7532
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m35s[0m 44ms/step - accuracy: 0.0731 - loss: 3.1952
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m35s[0m 44ms/step - accuracy: 0.0731 - loss: 3.1951
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m35s[0m 44ms/step - accuracy: 0.0731 - loss: 3.1951
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2224 - loss: 2.4553[32m [repeated 214x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m34s[0m 44ms/step - accuracy: 0.0733 - loss: 3.1945
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m34s[0m 44ms/step - accuracy: 0.0733 - loss: 3.1945[32m [repeated 199x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m109/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m20s[0m 45ms/step - accuracy: 0.1794 - loss: 2.6066
[1m111/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m20s[0m 45ms/step - accuracy: 0.1795 - loss: 2.6066[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 42ms/step - accuracy: 0.1883 - loss: 2.5265 - val_accuracy: 0.2490 - val_loss: 2.3070
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:38[0m 85ms/step - accuracy: 0.2500 - loss: 2.6826[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m33s[0m 44ms/step - accuracy: 0.0736 - loss: 3.1939
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m33s[0m 44ms/step - accuracy: 0.0736 - loss: 3.1939
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m33s[0m 44ms/step - accuracy: 0.0736 - loss: 3.1938
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m113/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m20s[0m 45ms/step - accuracy: 0.1796 - loss: 2.6065[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 34ms/step - accuracy: 0.1468 - loss: 2.8909
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 34ms/step - accuracy: 0.1468 - loss: 2.8909[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m400/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 43ms/step - accuracy: 0.1514 - loss: 2.7510[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m402/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 42ms/step - accuracy: 0.1514 - loss: 2.7509
[1m404/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 42ms/step - accuracy: 0.1515 - loss: 2.7508[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 34ms/step - accuracy: 0.1468 - loss: 2.8904[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 33ms/step - accuracy: 0.1469 - loss: 2.7754 - val_accuracy: 0.2216 - val_loss: 2.3993
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m86s[0m 68ms/step - accuracy: 0.1653 - loss: 2.7958 - val_accuracy: 0.3186 - val_loss: 2.1637
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.2188 - loss: 2.3697 
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.2083 - loss: 2.3601
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.2070 - loss: 2.3513
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2081 - loss: 2.3476
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2151 - loss: 2.3384
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m157/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 44ms/step - accuracy: 0.1816 - loss: 2.6031
[1m158/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 44ms/step - accuracy: 0.1816 - loss: 2.6030
[1m159/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 44ms/step - accuracy: 0.1817 - loss: 2.6029
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m31s[0m 44ms/step - accuracy: 0.0743 - loss: 3.1921
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m31s[0m 44ms/step - accuracy: 0.0743 - loss: 3.1921
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m31s[0m 44ms/step - accuracy: 0.0743 - loss: 3.1921
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.2214 - loss: 2.3296
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.2286 - loss: 2.3262
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.2315 - loss: 2.3257
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  12/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.2317 - loss: 2.3270
[36m(train_cnn_ray_tune pid=2697863)[0m Epoch 2/29[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.2310 - loss: 2.3285
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2317 - loss: 2.3274
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m168/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 44ms/step - accuracy: 0.1820 - loss: 2.6021
[1m169/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 44ms/step - accuracy: 0.1821 - loss: 2.6020
[1m170/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 44ms/step - accuracy: 0.1821 - loss: 2.6018
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2324 - loss: 2.3273
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2334 - loss: 2.3274
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2343 - loss: 2.3283
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2348 - loss: 2.3303
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2354 - loss: 2.3322
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2360 - loss: 2.3342
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2366 - loss: 2.3365
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2369 - loss: 2.3366
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:51[0m 97ms/step - accuracy: 0.2031 - loss: 2.7266 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:30[0m 79ms/step - accuracy: 0.1771 - loss: 2.7661
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2370 - loss: 2.3374
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.2372 - loss: 2.3378
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.2118 - loss: 2.7603 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.1731 - loss: 2.7735
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m20s[0m 40ms/step - accuracy: 0.1701 - loss: 2.6483
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m20s[0m 40ms/step - accuracy: 0.1701 - loss: 2.6483
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m20s[0m 40ms/step - accuracy: 0.1701 - loss: 2.6483
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m31s[0m 45ms/step - accuracy: 0.1678 - loss: 2.6572[32m [repeated 258x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m30s[0m 45ms/step - accuracy: 0.0750 - loss: 3.1903
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m30s[0m 45ms/step - accuracy: 0.0750 - loss: 3.1903[32m [repeated 220x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m309/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 49ms/step - accuracy: 0.1367 - loss: 2.9907
[1m310/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 49ms/step - accuracy: 0.1367 - loss: 2.9907[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:07[0m 110ms/step - accuracy: 0.2500 - loss: 2.3171[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m311/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 49ms/step - accuracy: 0.1367 - loss: 2.9907[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 34ms/step - accuracy: 0.1469 - loss: 2.8873
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 34ms/step - accuracy: 0.1469 - loss: 2.8872[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m532/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 31ms/step - accuracy: 0.1954 - loss: 2.4391[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m508/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 43ms/step - accuracy: 0.1522 - loss: 2.7457
[1m510/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 43ms/step - accuracy: 0.1522 - loss: 2.7457[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 34ms/step - accuracy: 0.1469 - loss: 2.8872[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 34ms/step - accuracy: 0.1683 - loss: 2.5971 - val_accuracy: 0.2388 - val_loss: 2.2995[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 42ms/step - accuracy: 0.2674 - loss: 2.3419  
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  62/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.1872 - loss: 2.6054[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 46ms/step - accuracy: 0.1906 - loss: 2.5502 - val_accuracy: 0.2396 - val_loss: 2.3137
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.2392 - loss: 2.3604
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2392 - loss: 2.3605[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 115ms/step - accuracy: 0.1250 - loss: 2.6774
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 85ms/step - accuracy: 0.1328 - loss: 2.6367  
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 4/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m555/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1525 - loss: 2.7439
[1m556/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1525 - loss: 2.7439
[1m557/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1525 - loss: 2.7439
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 39ms/step - accuracy: 0.2228 - loss: 2.4512[32m [repeated 305x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m26s[0m 45ms/step - accuracy: 0.0760 - loss: 3.1878
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m26s[0m 45ms/step - accuracy: 0.0761 - loss: 3.1878[32m [repeated 235x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 67/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 47ms/step - accuracy: 0.1958 - loss: 2.4887
[1m 69/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 46ms/step - accuracy: 0.1960 - loss: 2.4886[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 72/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 46ms/step - accuracy: 0.1965 - loss: 2.4881[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 113ms/step - accuracy: 0.1250 - loss: 2.6913
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.1406 - loss: 2.6475  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.1547 - loss: 2.5949
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1640 - loss: 2.8032
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1640 - loss: 2.8032
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1641 - loss: 2.8030
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.1641 - loss: 2.8030
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m420/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1367 - loss: 2.9910[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.1597 - loss: 2.6051  
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m422/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1367 - loss: 2.9910
[1m423/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1367 - loss: 2.9910[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.1641 - loss: 2.8030[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.1641 - loss: 2.8029
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.1641 - loss: 2.8029
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.1641 - loss: 2.8029
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.1641 - loss: 2.8028
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m44s[0m 38ms/step - accuracy: 0.1469 - loss: 2.8871 - val_accuracy: 0.2222 - val_loss: 2.3974
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.1914 - loss: 2.5645[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 37ms/step - accuracy: 0.1956 - loss: 2.4384 - val_accuracy: 0.2791 - val_loss: 2.2283
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 49ms/step - accuracy: 0.1526 - loss: 2.7430 - val_accuracy: 0.2212 - val_loss: 2.3446
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 62ms/step - accuracy: 0.2366 - loss: 2.3699
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 62ms/step - accuracy: 0.2365 - loss: 2.3700[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 109ms/step - accuracy: 0.0625 - loss: 2.8781
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 31ms/step - accuracy: 0.0851 - loss: 2.7641  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m335/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 51ms/step - accuracy: 0.1864 - loss: 2.5893
[1m336/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 51ms/step - accuracy: 0.1864 - loss: 2.5892
[1m337/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 51ms/step - accuracy: 0.1865 - loss: 2.5891
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 175/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 61ms/step - accuracy: 0.2362 - loss: 2.3701 
[1m 176/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 61ms/step - accuracy: 0.2361 - loss: 2.3701
[36m(train_cnn_ray_tune pid=2697882)[0m Epoch 4/16[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 32ms/step - accuracy: 0.2026 - loss: 2.5004
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 32ms/step - accuracy: 0.2025 - loss: 2.5005
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 32ms/step - accuracy: 0.2025 - loss: 2.5006
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 41ms/step - accuracy: 0.1698 - loss: 2.6481[32m [repeated 287x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m22s[0m 46ms/step - accuracy: 0.0769 - loss: 3.1862
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m22s[0m 46ms/step - accuracy: 0.0769 - loss: 3.1862[32m [repeated 210x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m384/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 52ms/step - accuracy: 0.1868 - loss: 2.5866
[1m385/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 52ms/step - accuracy: 0.1868 - loss: 2.5866[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m387/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.1868 - loss: 2.5865 
[1m388/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.1868 - loss: 2.5864
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 73/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 46ms/step - accuracy: 0.1592 - loss: 2.6406[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:47[0m 145ms/step - accuracy: 0.1250 - loss: 2.8306
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 39ms/step - accuracy: 0.1644 - loss: 2.8017
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 39ms/step - accuracy: 0.1644 - loss: 2.8017[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m515/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 50ms/step - accuracy: 0.1370 - loss: 2.9896[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m515/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 37ms/step - accuracy: 0.1986 - loss: 2.4439
[1m517/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 37ms/step - accuracy: 0.1986 - loss: 2.4439[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 39ms/step - accuracy: 0.1645 - loss: 2.8015[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1698 - loss: 2.6479 
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1698 - loss: 2.6479
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.1918 - loss: 2.5524[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.1918 - loss: 2.5519
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.1918 - loss: 2.5518[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m23s[0m 46ms/step - accuracy: 0.1594 - loss: 2.8161
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m23s[0m 46ms/step - accuracy: 0.1594 - loss: 2.8161
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m23s[0m 46ms/step - accuracy: 0.1594 - loss: 2.8160[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m23s[0m 47ms/step - accuracy: 0.1705 - loss: 2.7273[32m [repeated 287x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m57s[0m 64ms/step - accuracy: 0.1922 - loss: 2.5469
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m56s[0m 64ms/step - accuracy: 0.1922 - loss: 2.5468[32m [repeated 235x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m273/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.2165 - loss: 2.3920
[1m275/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.2164 - loss: 2.3919[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m279/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.2164 - loss: 2.3918[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.1648 - loss: 2.8004
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.1648 - loss: 2.8004[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m485/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 53ms/step - accuracy: 0.1873 - loss: 2.5829[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m486/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 53ms/step - accuracy: 0.1873 - loss: 2.5829
[1m487/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 53ms/step - accuracy: 0.1873 - loss: 2.5828[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 42ms/step - accuracy: 0.1700 - loss: 2.6467[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.1989 - loss: 2.4434 - val_accuracy: 0.2450 - val_loss: 2.3063
[36m(train_cnn_ray_tune pid=2697828)[0m Epoch 5/27
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 135ms/step - accuracy: 0.1875 - loss: 2.5645
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2049 - loss: 2.4658  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 42ms/step - accuracy: 0.2064 - loss: 2.4564
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 64ms/step - accuracy: 0.1919 - loss: 2.5517
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 64ms/step - accuracy: 0.1919 - loss: 2.5515 
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m17s[0m 46ms/step - accuracy: 0.0777 - loss: 3.1839
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m17s[0m 46ms/step - accuracy: 0.0777 - loss: 3.1838
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m17s[0m 46ms/step - accuracy: 0.0777 - loss: 3.1838
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1612 - loss: 2.6808 
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1612 - loss: 2.6808
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m51s[0m 63ms/step - accuracy: 0.1931 - loss: 2.5388[32m [repeated 272x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m29s[0m 37ms/step - accuracy: 0.1442 - loss: 2.8302
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m29s[0m 37ms/step - accuracy: 0.1442 - loss: 2.8301[32m [repeated 213x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m281/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 47ms/step - accuracy: 0.1612 - loss: 2.6450
[1m282/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 47ms/step - accuracy: 0.1612 - loss: 2.6451[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 45ms/step - accuracy: 0.1260 - loss: 2.9622[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 41ms/step - accuracy: 0.1202 - loss: 2.9774
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 41ms/step - accuracy: 0.1203 - loss: 2.9773[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 53ms/step - accuracy: 0.1877 - loss: 2.5799[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m451/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 35ms/step - accuracy: 0.2157 - loss: 2.3906
[1m453/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 35ms/step - accuracy: 0.2157 - loss: 2.3906[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 33ms/step - accuracy: 0.1940 - loss: 2.5070
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 33ms/step - accuracy: 0.1940 - loss: 2.5070
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 33ms/step - accuracy: 0.1940 - loss: 2.5070
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1612 - loss: 2.6800[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 57ms/step - accuracy: 0.1374 - loss: 2.9880 - val_accuracy: 0.1695 - val_loss: 2.6257
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 4/28
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:23[0m 144ms/step - accuracy: 0.1250 - loss: 2.9199
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.1181 - loss: 2.9837  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 49ms/step - accuracy: 0.1178 - loss: 2.9936
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m52s[0m 45ms/step - accuracy: 0.2243 - loss: 2.4441 - val_accuracy: 0.3099 - val_loss: 2.0984
[36m(train_cnn_ray_tune pid=2697873)[0m Epoch 3/28
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43[0m 90ms/step - accuracy: 0.1875 - loss: 2.3364
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.2257 - loss: 2.3810 
Trial status: 20 RUNNING
Current time: 2025-11-07 12:42:21. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m362/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.1614 - loss: 2.6461 
[1m364/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.1614 - loss: 2.6462
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.1625 - loss: 2.8009 
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.1625 - loss: 2.8009
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 60ms/step - accuracy: 0.1877 - loss: 2.5799 - val_accuracy: 0.2392 - val_loss: 2.2800
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:34[0m 163ms/step - accuracy: 0.2500 - loss: 2.5583
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.2734 - loss: 2.4616  
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m45s[0m 62ms/step - accuracy: 0.1941 - loss: 2.5326[32m [repeated 225x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m22s[0m 36ms/step - accuracy: 0.1470 - loss: 2.8236
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m22s[0m 36ms/step - accuracy: 0.1471 - loss: 2.8235[32m [repeated 178x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m227/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.2077 - loss: 2.4096
[1m229/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.2078 - loss: 2.4096[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m236/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 37ms/step - accuracy: 0.2078 - loss: 2.4094[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 46ms/step - accuracy: 0.0793 - loss: 3.1780
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 46ms/step - accuracy: 0.0793 - loss: 3.1780[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m538/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 45ms/step - accuracy: 0.2034 - loss: 2.4859[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m421/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 45ms/step - accuracy: 0.1616 - loss: 2.6464
[1m423/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 45ms/step - accuracy: 0.1616 - loss: 2.6464[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 36ms/step - accuracy: 0.1474 - loss: 2.8223
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 36ms/step - accuracy: 0.1475 - loss: 2.8222
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 36ms/step - accuracy: 0.1475 - loss: 2.8222[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 47ms/step - accuracy: 0.1630 - loss: 2.7980[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1924 - loss: 2.5062 
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1924 - loss: 2.5062
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1923 - loss: 2.5062
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1923 - loss: 2.5062
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1923 - loss: 2.5061
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 39ms/step - accuracy: 0.1354 - loss: 2.7760  
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m54s[0m 47ms/step - accuracy: 0.1702 - loss: 2.6450 - val_accuracy: 0.2430 - val_loss: 2.2979[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 3/27[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:30[0m 130ms/step - accuracy: 0.1250 - loss: 2.8561
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.2153 - loss: 2.3902 - val_accuracy: 0.2879 - val_loss: 2.2226
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 114ms/step - accuracy: 0.2188 - loss: 2.2679
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2205 - loss: 2.3196  
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 44ms/step - accuracy: 0.1984 - loss: 2.5746[32m [repeated 208x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m27s[0m 57ms/step - accuracy: 0.1841 - loss: 2.6000
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m27s[0m 57ms/step - accuracy: 0.1841 - loss: 2.6000[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:16[0m 118ms/step - accuracy: 0.1250 - loss: 2.5658
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.0938 - loss: 2.7770 
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m111/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 50ms/step - accuracy: 0.1959 - loss: 2.5049
[1m112/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 50ms/step - accuracy: 0.1959 - loss: 2.5048[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 49ms/step - accuracy: 0.2034 - loss: 2.4854 - val_accuracy: 0.2426 - val_loss: 2.3011
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.0972 - loss: 2.8657
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.0964 - loss: 2.9185
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m115/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 50ms/step - accuracy: 0.1960 - loss: 2.5047[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 105ms/step - accuracy: 0.1562 - loss: 2.2270
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.1046 - loss: 2.9337
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.1132 - loss: 2.9337
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1224 - loss: 2.9336
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.1916 - loss: 2.5054
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.1916 - loss: 2.5054[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1281 - loss: 2.9223
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1299 - loss: 2.9143
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m534/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 45ms/step - accuracy: 0.1618 - loss: 2.6462[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1342 - loss: 2.9005
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1361 - loss: 2.8970
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m394/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 36ms/step - accuracy: 0.2089 - loss: 2.4063
[1m395/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 36ms/step - accuracy: 0.2089 - loss: 2.4063[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.1483 - loss: 2.8196
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.1483 - loss: 2.8195
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.1484 - loss: 2.8195
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.1402 - loss: 2.8889 
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 48ms/step - accuracy: 0.1754 - loss: 2.7036[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.1181 - loss: 2.8769  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.1208 - loss: 2.8249
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 34ms/step - accuracy: 0.1612 - loss: 2.6760 - val_accuracy: 0.2245 - val_loss: 2.3709[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m Epoch 4/18[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m32s[0m 38ms/step - accuracy: 0.2586 - loss: 2.3196[32m [repeated 192x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m33s[0m 61ms/step - accuracy: 0.1960 - loss: 2.5236
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m33s[0m 61ms/step - accuracy: 0.1960 - loss: 2.5236[32m [repeated 155x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m363/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 48ms/step - accuracy: 0.1479 - loss: 2.9118
[1m365/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 48ms/step - accuracy: 0.1480 - loss: 2.9116[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m217/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 50ms/step - accuracy: 0.1982 - loss: 2.5025[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:54[0m 100ms/step - accuracy: 0.1250 - loss: 3.1273
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 50ms/step - accuracy: 0.1619 - loss: 2.6459 - val_accuracy: 0.2370 - val_loss: 2.3239
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 107ms/step - accuracy: 0.2188 - loss: 2.6221
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.1875 - loss: 2.6733  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.1908 - loss: 2.6478
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 47ms/step - accuracy: 0.1764 - loss: 2.6980
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 47ms/step - accuracy: 0.1764 - loss: 2.6978[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m373/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1482 - loss: 2.9111[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m375/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1482 - loss: 2.9110
[1m376/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1482 - loss: 2.9109[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 48ms/step - accuracy: 0.1765 - loss: 2.6975[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m Epoch 5/16
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m60s[0m 52ms/step - accuracy: 0.0800 - loss: 3.1750 - val_accuracy: 0.1221 - val_loss: 2.7331
[36m(train_cnn_ray_tune pid=2697871)[0m Epoch 3/17
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46[0m 92ms/step - accuracy: 0.1875 - loss: 2.4742
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 39ms/step - accuracy: 0.2153 - loss: 2.4234 
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1250 - loss: 2.5719 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 42ms/step - accuracy: 0.1289 - loss: 2.5900 
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m35s[0m 41ms/step - accuracy: 0.1905 - loss: 2.5566[32m [repeated 192x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m27s[0m 61ms/step - accuracy: 0.1972 - loss: 2.5190
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m27s[0m 61ms/step - accuracy: 0.1972 - loss: 2.5190[32m [repeated 171x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m26s[0m 38ms/step - accuracy: 0.2569 - loss: 2.3192
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m235/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 42ms/step - accuracy: 0.2092 - loss: 2.4204
[1m236/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 42ms/step - accuracy: 0.2092 - loss: 2.4205[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m118/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 41ms/step - accuracy: 0.1769 - loss: 2.5995[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.2093 - loss: 2.4036 - val_accuracy: 0.2635 - val_loss: 2.2841
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 105ms/step - accuracy: 0.1562 - loss: 2.6972[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2066 - loss: 2.5484  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2102 - loss: 2.5249
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.1493 - loss: 2.4745  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.1590 - loss: 2.4592
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 35ms/step - accuracy: 0.1504 - loss: 2.8115
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 35ms/step - accuracy: 0.1504 - loss: 2.8114[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m480/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 48ms/step - accuracy: 0.1500 - loss: 2.9061[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m432/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.2221 - loss: 2.3614
[1m434/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 31ms/step - accuracy: 0.2221 - loss: 2.3613[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 35ms/step - accuracy: 0.1505 - loss: 2.8112[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m  64/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 31ms/step - accuracy: 0.1904 - loss: 2.4303
[1m  66/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 31ms/step - accuracy: 0.1903 - loss: 2.4306
[1m  68/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 31ms/step - accuracy: 0.1903 - loss: 2.4307
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 36ms/step - accuracy: 0.1908 - loss: 2.5039 - val_accuracy: 0.2623 - val_loss: 2.2738[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 4/24[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m380/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1990 - loss: 2.5050 
[1m381/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1990 - loss: 2.5049
[36m(train_cnn_ray_tune pid=2697828)[0m 
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m121/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.2133 - loss: 2.3910
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 44ms/step - accuracy: 0.2144 - loss: 2.4603[32m [repeated 277x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 60ms/step - accuracy: 0.1982 - loss: 2.5147
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m22s[0m 60ms/step - accuracy: 0.1982 - loss: 2.5147[32m [repeated 212x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:52[0m 97ms/step - accuracy: 0.1875 - loss: 2.3407
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 40ms/step - accuracy: 0.2118 - loss: 2.4113 
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.1853 - loss: 2.5913 
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.1853 - loss: 2.5913
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m242/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 41ms/step - accuracy: 0.1754 - loss: 2.6002
[1m243/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 41ms/step - accuracy: 0.1754 - loss: 2.6002[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m140/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 38ms/step - accuracy: 0.2138 - loss: 2.3878[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:55[0m 100ms/step - accuracy: 0.1250 - loss: 2.5075
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.1854 - loss: 2.5912
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.1854 - loss: 2.5912[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m372/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 42ms/step - accuracy: 0.2113 - loss: 2.4238[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m424/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 50ms/step - accuracy: 0.1992 - loss: 2.5043
[1m426/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 50ms/step - accuracy: 0.1992 - loss: 2.5043[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 56ms/step - accuracy: 0.1854 - loss: 2.5910[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m20s[0m 35ms/step - accuracy: 0.2235 - loss: 2.3566 - val_accuracy: 0.3180 - val_loss: 2.1770
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 44ms/step - accuracy: 0.1690 - loss: 2.6352
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 44ms/step - accuracy: 0.1691 - loss: 2.6348
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 44ms/step - accuracy: 0.1693 - loss: 2.6345
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 111ms/step - accuracy: 0.1250 - loss: 2.4796
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.1510 - loss: 2.4662  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 31ms/step - accuracy: 0.1806 - loss: 2.4179
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m61s[0m 53ms/step - accuracy: 0.1771 - loss: 2.6943 - val_accuracy: 0.2621 - val_loss: 2.2873
[36m(train_cnn_ray_tune pid=2697881)[0m Epoch 7/20[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m17s[0m 60ms/step - accuracy: 0.1991 - loss: 2.5109[32m [repeated 254x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 30ms/step - accuracy: 0.1911 - loss: 2.4508
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m25s[0m 30ms/step - accuracy: 0.1911 - loss: 2.4509[32m [repeated 234x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 92/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 31ms/step - accuracy: 0.2254 - loss: 2.3204
[1m 94/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 30ms/step - accuracy: 0.2254 - loss: 2.3205[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 24/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 54ms/step - accuracy: 0.1537 - loss: 2.8290[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m45s[0m 39ms/step - accuracy: 0.1511 - loss: 2.8079 - val_accuracy: 0.2192 - val_loss: 2.3570
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 55ms/step - accuracy: 0.1855 - loss: 2.5892
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 55ms/step - accuracy: 0.1855 - loss: 2.5892[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m379/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 41ms/step - accuracy: 0.1750 - loss: 2.5986[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.0729 - loss: 2.7897      
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.0988 - loss: 2.7849
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m381/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 41ms/step - accuracy: 0.1749 - loss: 2.5986
[1m382/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 41ms/step - accuracy: 0.1749 - loss: 2.5986[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 55ms/step - accuracy: 0.1855 - loss: 2.5890[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 45ms/step - accuracy: 0.2083 - loss: 2.4395   
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 54ms/step - accuracy: 0.1509 - loss: 2.9033 - val_accuracy: 0.1866 - val_loss: 2.5414
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:21:46[0m 26s/step - accuracy: 0.2500 - loss: 2.3816[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 82ms/step - accuracy: 0.1797 - loss: 2.5813  
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 69ms/step - accuracy: 0.1649 - loss: 2.6452
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 35ms/step - accuracy: 0.1463 - loss: 2.7055
[1m  60/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 35ms/step - accuracy: 0.1466 - loss: 2.7052
[1m  61/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 36ms/step - accuracy: 0.1469 - loss: 2.7050
Trial status: 20 RUNNING
Current time: 2025-11-07 12:42:51. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 4/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m12s[0m 60ms/step - accuracy: 0.1998 - loss: 2.5074[32m [repeated 277x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 31ms/step - accuracy: 0.1914 - loss: 2.4553
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m21s[0m 31ms/step - accuracy: 0.1914 - loss: 2.4553[32m [repeated 251x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m122/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.1544 - loss: 2.8591
[1m124/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.1543 - loss: 2.8594[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m240/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 33ms/step - accuracy: 0.2282 - loss: 2.3192[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 58ms/step - accuracy: 0.2376 - loss: 2.3424
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 58ms/step - accuracy: 0.2376 - loss: 2.3424[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m434/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 37ms/step - accuracy: 0.2173 - loss: 2.3690[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m490/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 42ms/step - accuracy: 0.1741 - loss: 2.5981
[1m492/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 42ms/step - accuracy: 0.1741 - loss: 2.5980[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.2547 - loss: 2.3166[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m272/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2292 - loss: 2.3179 
[1m274/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.2292 - loss: 2.3178
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 57ms/step - accuracy: 0.2000 - loss: 2.5015 - val_accuracy: 0.2488 - val_loss: 2.2776
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 106ms/step - accuracy: 0.1250 - loss: 2.5004[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 6/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 30ms/step - accuracy: 0.1918 - loss: 2.4570
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 30ms/step - accuracy: 0.1918 - loss: 2.4570
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 30ms/step - accuracy: 0.1918 - loss: 2.4570
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 203/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m37s[0m 39ms/step - accuracy: 0.1736 - loss: 2.7112[32m [repeated 202x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 34ms/step - accuracy: 0.1548 - loss: 2.7254
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m29s[0m 34ms/step - accuracy: 0.1548 - loss: 2.7255[32m [repeated 210x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 41ms/step - accuracy: 0.0625 - loss: 3.0504   
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 42ms/step - accuracy: 0.0650 - loss: 3.0946
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 67/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 49ms/step - accuracy: 0.2084 - loss: 2.4452
[1m 68/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 49ms/step - accuracy: 0.2084 - loss: 2.4453[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m232/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 49ms/step - accuracy: 0.1548 - loss: 2.8656[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 58ms/step - accuracy: 0.2382 - loss: 2.3398
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 58ms/step - accuracy: 0.2382 - loss: 2.3398[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m575/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.2186 - loss: 2.3655[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m409/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.2314 - loss: 2.3162
[1m411/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.2314 - loss: 2.3162[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 59ms/step - accuracy: 0.2010 - loss: 2.5026[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 47ms/step - accuracy: 0.2136 - loss: 2.4227 - val_accuracy: 0.2621 - val_loss: 2.2671
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 47ms/step - accuracy: 0.1739 - loss: 2.5970 - val_accuracy: 0.2444 - val_loss: 2.3125
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 142ms/step - accuracy: 0.1562 - loss: 2.6552
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 38ms/step - accuracy: 0.1997 - loss: 2.5870  
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:07:56[0m 22s/step - accuracy: 0.0625 - loss: 3.0732
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m72s[0m 62ms/step - accuracy: 0.1857 - loss: 2.5875 - val_accuracy: 0.2357 - val_loss: 2.2882
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:04[0m 160ms/step - accuracy: 0.1875 - loss: 2.3672
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 72ms/step - accuracy: 0.1875 - loss: 2.3607 
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 64ms/step - accuracy: 0.1736 - loss: 2.4052
[36m(train_cnn_ray_tune pid=2697817)[0m Epoch 3/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 66ms/step - accuracy: 0.1654 - loss: 2.4186
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.1573 - loss: 2.4337
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1481 - loss: 2.4654
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1481 - loss: 2.4784
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1494 - loss: 2.4844
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1507 - loss: 2.4932
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1530 - loss: 2.4989
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  12/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1550 - loss: 2.5019
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1584 - loss: 2.5114
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1595 - loss: 2.5159
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1628 - loss: 2.5192
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1640 - loss: 2.5199
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1652 - loss: 2.5204
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.1667 - loss: 2.5211
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.1672 - loss: 2.5221
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.1677 - loss: 2.5222
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.1683 - loss: 2.5221
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.1691 - loss: 2.5216
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1699 - loss: 2.5208
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1704 - loss: 2.5208
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.1710 - loss: 2.5206
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.1716 - loss: 2.5201
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  31/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.1730 - loss: 2.5184
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m27s[0m 45ms/step - accuracy: 0.2004 - loss: 2.5013
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m27s[0m 45ms/step - accuracy: 0.2004 - loss: 2.5013
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m27s[0m 45ms/step - accuracy: 0.2004 - loss: 2.5013
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  32/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.1737 - loss: 2.5175
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 30ms/step - accuracy: 0.1921 - loss: 2.4574[32m [repeated 237x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  97/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 48ms/step - accuracy: 0.0926 - loss: 3.1142
[1m  98/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 48ms/step - accuracy: 0.0927 - loss: 3.1138[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  34/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1751 - loss: 2.5162
[1m  35/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1756 - loss: 2.5157
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  36/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1762 - loss: 2.5149
[1m  37/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.1768 - loss: 2.5142
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  39/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.1780 - loss: 2.5128
[1m  41/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.1788 - loss: 2.5121
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  42/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.1792 - loss: 2.5119
[1m  43/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.1797 - loss: 2.5117
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  44/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.1801 - loss: 2.5115
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 70/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 42ms/step - accuracy: 0.1767 - loss: 2.5631
[1m 71/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 43ms/step - accuracy: 0.1766 - loss: 2.5633[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 38/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2191 - loss: 2.3420[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.1809 - loss: 2.5112
[1m  47/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.1812 - loss: 2.5112
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1815 - loss: 2.5110
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.1819 - loss: 2.5108
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.1825 - loss: 2.5105
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1828 - loss: 2.5105
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1921 - loss: 2.4575
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1921 - loss: 2.4575[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1830 - loss: 2.5105
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m562/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.2327 - loss: 2.3145[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1832 - loss: 2.5105
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1835 - loss: 2.5105
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m33s[0m 47ms/step - accuracy: 0.1923 - loss: 2.5485
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m33s[0m 47ms/step - accuracy: 0.1923 - loss: 2.5484
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m33s[0m 47ms/step - accuracy: 0.1923 - loss: 2.5484
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m572/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.2327 - loss: 2.3144
[1m575/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.2328 - loss: 2.3144[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 59ms/step - accuracy: 0.2019 - loss: 2.4994[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1837 - loss: 2.5105
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1838 - loss: 2.5106
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1841 - loss: 2.5107
[1m  60/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.1842 - loss: 2.5106
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  62/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.1844 - loss: 2.5104
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  64/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.1846 - loss: 2.5100
[1m  65/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.1847 - loss: 2.5099
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  67/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 57ms/step - accuracy: 0.1849 - loss: 2.5093
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  69/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.1851 - loss: 2.5087
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  71/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1852 - loss: 2.5082
[1m  72/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1854 - loss: 2.5079
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  73/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1854 - loss: 2.5076
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.1857 - loss: 2.5068
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 55ms/step - accuracy: 0.1859 - loss: 2.5062 
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 55ms/step - accuracy: 0.1860 - loss: 2.5060
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 42ms/step - accuracy: 0.2187 - loss: 2.3654 - val_accuracy: 0.2698 - val_loss: 2.2452
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 35ms/step - accuracy: 0.2328 - loss: 2.3144 - val_accuracy: 0.3141 - val_loss: 2.1492
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 71ms/step - accuracy: 0.2500 - loss: 2.2091
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 79ms/step - accuracy: 0.1875 - loss: 2.3076
[36m(train_cnn_ray_tune pid=2697881)[0m Epoch 8/20[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m73s[0m 64ms/step - accuracy: 0.2385 - loss: 2.3388 - val_accuracy: 0.3167 - val_loss: 2.1112
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:12[0m 115ms/step - accuracy: 0.3750 - loss: 2.0946
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.3594 - loss: 2.1521 
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m19s[0m 44ms/step - accuracy: 0.1851 - loss: 2.6034[32m [repeated 202x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m42s[0m 45ms/step - accuracy: 0.0970 - loss: 3.0900
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m42s[0m 45ms/step - accuracy: 0.0970 - loss: 3.0899[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 64ms/step - accuracy: 0.3299 - loss: 2.2201
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.3060 - loss: 2.2907
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 36ms/step - accuracy: 0.1250 - loss: 2.5581  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 36ms/step - accuracy: 0.1369 - loss: 2.5216
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2967 - loss: 2.3017
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2939 - loss: 2.3022
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.2933 - loss: 2.3004
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2946 - loss: 2.2952
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.2945 - loss: 2.2921
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.2936 - loss: 2.2907
[1m  12/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.2926 - loss: 2.2918
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.2904 - loss: 2.2950
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m258/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 52ms/step - accuracy: 0.2091 - loss: 2.4518
[1m260/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 52ms/step - accuracy: 0.2091 - loss: 2.4519[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 89/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 29ms/step - accuracy: 0.2418 - loss: 2.3002[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2885 - loss: 2.2990
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.2870 - loss: 2.3006
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2842 - loss: 2.2998
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2804 - loss: 2.2999
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.2788 - loss: 2.2998
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 30ms/step - accuracy: 0.1922 - loss: 2.4573
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 30ms/step - accuracy: 0.1923 - loss: 2.4573[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2774 - loss: 2.2996
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.2761 - loss: 2.2994
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m460/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.1562 - loss: 2.8592[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 53ms/step - accuracy: 0.1876 - loss: 2.5049
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 53ms/step - accuracy: 0.1877 - loss: 2.5048
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 53ms/step - accuracy: 0.1877 - loss: 2.5048[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.2751 - loss: 2.2987
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2741 - loss: 2.2978
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m454/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.1562 - loss: 2.8594
[1m455/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.1562 - loss: 2.8594[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 30ms/step - accuracy: 0.1923 - loss: 2.4572[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.2729 - loss: 2.2975
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2717 - loss: 2.2976
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2705 - loss: 2.2985
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.2696 - loss: 2.2989
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2690 - loss: 2.2993
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2682 - loss: 2.2998
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  31/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2673 - loss: 2.3003
[1m  32/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2666 - loss: 2.3004
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  33/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2658 - loss: 2.3004
[1m  34/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2650 - loss: 2.3003
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  35/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2641 - loss: 2.3007
[1m  36/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2634 - loss: 2.3011
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  37/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2627 - loss: 2.3015
[1m  38/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2620 - loss: 2.3017
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  39/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2614 - loss: 2.3020
[1m  41/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2603 - loss: 2.3024
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 42ms/step - accuracy: 0.2535 - loss: 2.2580 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.2521 - loss: 2.2402
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  42/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2598 - loss: 2.3023
[1m  43/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2594 - loss: 2.3021
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  44/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2590 - loss: 2.3019
[1m  45/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2586 - loss: 2.3017
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2582 - loss: 2.3014
[1m  47/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2580 - loss: 2.3010
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2578 - loss: 2.3008
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2575 - loss: 2.3009
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2569 - loss: 2.3008
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2566 - loss: 2.3007
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.2562 - loss: 2.3006
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44[0m 90ms/step - accuracy: 0.1875 - loss: 2.2945[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2555 - loss: 2.3004
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2552 - loss: 2.3003
[36m(train_cnn_ray_tune pid=2697873)[0m Epoch 4/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2549 - loss: 2.3002
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2543 - loss: 2.3000
[1m  60/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2541 - loss: 2.2999
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  61/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2538 - loss: 2.2999
[1m  62/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2535 - loss: 2.2999
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  64/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2530 - loss: 2.2999
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  66/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.2526 - loss: 2.2998
[1m  67/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.2523 - loss: 2.2998
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  68/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.2521 - loss: 2.2998
[1m  69/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2519 - loss: 2.2997
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  70/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.2517 - loss: 2.2997
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 30ms/step - accuracy: 0.1925 - loss: 2.4568
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 30ms/step - accuracy: 0.1925 - loss: 2.4568
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 30ms/step - accuracy: 0.1925 - loss: 2.4568
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  71/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2516 - loss: 2.2996
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  72/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2514 - loss: 2.2995
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  73/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2513 - loss: 2.2994
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  74/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2511 - loss: 2.2992
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2510 - loss: 2.2991
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2508 - loss: 2.2988
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.2505 - loss: 2.2986
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.2505 - loss: 2.2984
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.2504 - loss: 2.2981
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m77s[0m 66ms/step - accuracy: 0.2019 - loss: 2.4993 - val_accuracy: 0.3002 - val_loss: 2.1781[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.2500 - loss: 2.2977
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.2499 - loss: 2.2976
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:34[0m 186ms/step - accuracy: 0.3125 - loss: 2.3362
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:37[0m 84ms/step - accuracy: 0.2656 - loss: 2.3576 
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m23s[0m 47ms/step - accuracy: 0.1948 - loss: 2.5373[32m [repeated 234x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m21s[0m 39ms/step - accuracy: 0.1755 - loss: 2.7126
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m21s[0m 39ms/step - accuracy: 0.1755 - loss: 2.7126[32m [repeated 194x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 68ms/step - accuracy: 0.2638 - loss: 2.3624
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 68ms/step - accuracy: 0.2656 - loss: 2.3580[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  93/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.2492 - loss: 2.2969
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  95/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.2491 - loss: 2.2968
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m231/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m11s[0m 33ms/step - accuracy: 0.2412 - loss: 2.2970
[1m235/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 33ms/step - accuracy: 0.2411 - loss: 2.2972[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m361/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 51ms/step - accuracy: 0.2094 - loss: 2.4529[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.1363 - loss: 2.8738
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 39ms/step - accuracy: 0.1364 - loss: 2.8738[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m565/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 48ms/step - accuracy: 0.1569 - loss: 2.8562[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 45ms/step - accuracy: 0.1990 - loss: 2.5042
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 45ms/step - accuracy: 0.1990 - loss: 2.5042
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 45ms/step - accuracy: 0.1990 - loss: 2.5042[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m451/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.2239 - loss: 2.3958
[1m452/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.2239 - loss: 2.3958[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.1363 - loss: 2.8739[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m384/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2095 - loss: 2.4530 
[1m385/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2095 - loss: 2.4530
[36m(train_cnn_ray_tune pid=2697836)[0m Epoch 3/23
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 39ms/step - accuracy: 0.1363 - loss: 2.8741
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 39ms/step - accuracy: 0.1363 - loss: 2.8741
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 39ms/step - accuracy: 0.1363 - loss: 2.8741
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1564 - loss: 2.7317 
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.1564 - loss: 2.7317
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 54ms/step - accuracy: 0.1570 - loss: 2.8558 - val_accuracy: 0.2164 - val_loss: 2.4843
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 6/28
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 34ms/step - accuracy: 0.1926 - loss: 2.4566 - val_accuracy: 0.2621 - val_loss: 2.2576
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m18s[0m 47ms/step - accuracy: 0.1963 - loss: 2.5323[32m [repeated 240x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m32s[0m 46ms/step - accuracy: 0.0965 - loss: 3.0846
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m32s[0m 46ms/step - accuracy: 0.0965 - loss: 3.0846[32m [repeated 201x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  92/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2444 - loss: 2.3820
[1m  93/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2443 - loss: 2.3819[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 108ms/step - accuracy: 0.1875 - loss: 2.5936
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 50ms/step - accuracy: 0.1484 - loss: 2.6949  
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  97/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2439 - loss: 2.3814[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  6/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 43ms/step - accuracy: 0.1302 - loss: 2.7564
[1m  8/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 44ms/step - accuracy: 0.1325 - loss: 2.7475[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 10/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 47ms/step - accuracy: 0.1343 - loss: 2.7434[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:21[0m 123ms/step - accuracy: 0.1875 - loss: 2.1727
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2031 - loss: 2.3445 
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.1987 - loss: 2.5042
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.1987 - loss: 2.5042[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m472/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 36ms/step - accuracy: 0.2220 - loss: 2.3376[32m [repeated 127x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 33ms/step - accuracy: 0.1561 - loss: 2.7323
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 33ms/step - accuracy: 0.1561 - loss: 2.7323
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 33ms/step - accuracy: 0.1561 - loss: 2.7323[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m389/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 34ms/step - accuracy: 0.2410 - loss: 2.2955
[1m391/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 34ms/step - accuracy: 0.2410 - loss: 2.2955[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.1987 - loss: 2.5042[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 71ms/step - accuracy: 0.0000e+00 - loss: 3.0739 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.0000e+00 - loss: 3.1245 
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 31/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 49ms/step - accuracy: 0.1402 - loss: 2.7548
[1m 32/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 49ms/step - accuracy: 0.1405 - loss: 2.7554
[1m 33/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 50ms/step - accuracy: 0.1407 - loss: 2.7561
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 41ms/step - accuracy: 0.0128 - loss: 3.1477    
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.0232 - loss: 3.1399
Trial status: 20 RUNNING
Current time: 2025-11-07 12:43:21. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m512/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 52ms/step - accuracy: 0.2099 - loss: 2.4520
[1m513/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 52ms/step - accuracy: 0.2100 - loss: 2.4519
[1m514/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 52ms/step - accuracy: 0.2100 - loss: 2.4519
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 94/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 52ms/step - accuracy: 0.1484 - loss: 2.7846
[1m 95/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 52ms/step - accuracy: 0.1485 - loss: 2.7850
[1m 96/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 52ms/step - accuracy: 0.1486 - loss: 2.7853
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 48ms/step - accuracy: 0.2239 - loss: 2.3922 - val_accuracy: 0.2708 - val_loss: 2.2382
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 7/27[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 44ms/step - accuracy: 0.1364 - loss: 2.8738 - val_accuracy: 0.2335 - val_loss: 2.3867[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m28s[0m 46ms/step - accuracy: 0.0966 - loss: 3.0824[32m [repeated 264x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 144/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 35ms/step - accuracy: 0.2067 - loss: 2.4281
[1m 145/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 35ms/step - accuracy: 0.2068 - loss: 2.4281[32m [repeated 209x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 173/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 62ms/step - accuracy: 0.2390 - loss: 2.3782
[1m 174/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 62ms/step - accuracy: 0.2389 - loss: 2.3782[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 120ms/step - accuracy: 0.1250 - loss: 2.5466
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 51ms/step - accuracy: 0.1406 - loss: 2.5361  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 62ms/step - accuracy: 0.2392 - loss: 2.3784[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 181/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 62ms/step - accuracy: 0.2387 - loss: 2.3779 
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 62ms/step - accuracy: 0.2386 - loss: 2.3779
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m104/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 52ms/step - accuracy: 0.1490 - loss: 2.7876
[1m105/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 52ms/step - accuracy: 0.1491 - loss: 2.7878[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m106/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 52ms/step - accuracy: 0.1491 - loss: 2.7881[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:51[0m 148ms/step - accuracy: 0.0000e+00 - loss: 3.1181
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 45ms/step - accuracy: 0.1863 - loss: 2.6013
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 45ms/step - accuracy: 0.1863 - loss: 2.6013[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m559/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 52ms/step - accuracy: 0.2101 - loss: 2.4514[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 28ms/step - accuracy: 0.1732 - loss: 2.5655
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 29ms/step - accuracy: 0.1732 - loss: 2.5655
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 29ms/step - accuracy: 0.1732 - loss: 2.5655
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m558/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1761 - loss: 2.5647
[1m560/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.1761 - loss: 2.5647[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 34ms/step - accuracy: 0.1571 - loss: 2.7298[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 284/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m52s[0m 60ms/step - accuracy: 0.2502 - loss: 2.2725
[1m 285/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m52s[0m 60ms/step - accuracy: 0.2502 - loss: 2.2724
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m52s[0m 60ms/step - accuracy: 0.2502 - loss: 2.2723
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m50s[0m 60ms/step - accuracy: 0.2506 - loss: 2.2707
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m50s[0m 59ms/step - accuracy: 0.2507 - loss: 2.2706
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m50s[0m 59ms/step - accuracy: 0.2507 - loss: 2.2705
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 42ms/step - accuracy: 0.2231 - loss: 2.3359 - val_accuracy: 0.2801 - val_loss: 2.2369
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 106ms/step - accuracy: 0.2500 - loss: 2.2935
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.3420 - loss: 2.1883  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.3383 - loss: 2.1755
[36m(train_cnn_ray_tune pid=2697882)[0m Epoch 7/16[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m56s[0m 62ms/step - accuracy: 0.2377 - loss: 2.3722[32m [repeated 297x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.0969 - loss: 3.0805
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m23s[0m 47ms/step - accuracy: 0.0969 - loss: 3.0804[32m [repeated 207x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 179/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 62ms/step - accuracy: 0.2387 - loss: 2.3780
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 62ms/step - accuracy: 0.2387 - loss: 2.3780[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m106/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 49ms/step - accuracy: 0.2212 - loss: 2.3456
[1m107/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 49ms/step - accuracy: 0.2213 - loss: 2.3456
[1m108/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 49ms/step - accuracy: 0.2213 - loss: 2.3455
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 114ms/step - accuracy: 0.2188 - loss: 2.6447
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 59ms/step - accuracy: 0.2188 - loss: 2.6120  
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m115/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 49ms/step - accuracy: 0.2218 - loss: 2.3456
[1m116/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 49ms/step - accuracy: 0.2219 - loss: 2.3456[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 13/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 50ms/step - accuracy: 0.1928 - loss: 2.5867[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1985 - loss: 2.5244
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.1986 - loss: 2.5244[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 34ms/step - accuracy: 0.2414 - loss: 2.2932[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 52ms/step - accuracy: 0.2102 - loss: 2.4512
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 52ms/step - accuracy: 0.2102 - loss: 2.4512[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 46ms/step - accuracy: 0.1867 - loss: 2.6002[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.0968 - loss: 3.0809
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.0968 - loss: 3.0808
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.0968 - loss: 3.0808
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 58ms/step - accuracy: 0.2102 - loss: 2.4512 - val_accuracy: 0.2494 - val_loss: 2.2540[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:40[0m 174ms/step - accuracy: 0.2188 - loss: 2.6596[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 34ms/step - accuracy: 0.2073 - loss: 2.4202
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 34ms/step - accuracy: 0.2073 - loss: 2.4201
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 34ms/step - accuracy: 0.2073 - loss: 2.4201
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1741 - loss: 2.5604 
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.1741 - loss: 2.5603
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 6/28
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m19s[0m 47ms/step - accuracy: 0.0973 - loss: 3.0783[32m [repeated 216x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m51s[0m 62ms/step - accuracy: 0.2369 - loss: 2.3686
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m51s[0m 62ms/step - accuracy: 0.2369 - loss: 2.3685[32m [repeated 214x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 39/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 56ms/step - accuracy: 0.1996 - loss: 2.4560
[1m 40/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 56ms/step - accuracy: 0.1996 - loss: 2.4558
[1m 41/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 56ms/step - accuracy: 0.1997 - loss: 2.4556
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 83/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 54ms/step - accuracy: 0.1991 - loss: 2.4537
[1m 84/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 54ms/step - accuracy: 0.1991 - loss: 2.4536
[1m 85/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 54ms/step - accuracy: 0.1991 - loss: 2.4535
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m23s[0m 34ms/step - accuracy: 0.2070 - loss: 2.4201
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m23s[0m 34ms/step - accuracy: 0.2070 - loss: 2.4201
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 34ms/step - accuracy: 0.2070 - loss: 2.4202
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m120/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 47ms/step - accuracy: 0.1812 - loss: 2.5447
[1m122/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 47ms/step - accuracy: 0.1811 - loss: 2.5448[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 91/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m26s[0m 54ms/step - accuracy: 0.1988 - loss: 2.4530[32m [repeated 165x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m45s[0m 39ms/step - accuracy: 0.1575 - loss: 2.7289 - val_accuracy: 0.2190 - val_loss: 2.3506
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 5/26
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43[0m 89ms/step - accuracy: 0.0625 - loss: 2.5477
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.0799 - loss: 2.6229 
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 48ms/step - accuracy: 0.1994 - loss: 2.5211
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 48ms/step - accuracy: 0.1994 - loss: 2.5211[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 48ms/step - accuracy: 0.1994 - loss: 2.5209[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:55[0m 100ms/step - accuracy: 0.3750 - loss: 2.1103
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 67ms/step - accuracy: 0.3750 - loss: 2.1546 
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.3542 - loss: 2.1808
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.3137 - loss: 2.2472
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2764 - loss: 2.2984
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2643 - loss: 2.3169
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2550 - loss: 2.3358
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m285/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2566 - loss: 2.2457
[1m287/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2566 - loss: 2.2458
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2489 - loss: 2.3518
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2443 - loss: 2.3632
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m289/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2566 - loss: 2.2459
[1m290/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2565 - loss: 2.2459
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.2379 - loss: 2.3801
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.2332 - loss: 2.3929 
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m293/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2565 - loss: 2.2461
[1m295/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2564 - loss: 2.2462
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m297/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2564 - loss: 2.2463
[1m299/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2563 - loss: 2.2464
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2290 - loss: 2.4039
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m301/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2563 - loss: 2.2466
[1m303/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2562 - loss: 2.2467
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.2277 - loss: 2.4079
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m305/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2562 - loss: 2.2468
[1m307/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2561 - loss: 2.2469
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m385/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.1607 - loss: 2.7927 
[1m386/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.1607 - loss: 2.7927
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 52ms/step - accuracy: 0.2267 - loss: 2.4111 
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m387/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.1608 - loss: 2.7927
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m46s[0m 62ms/step - accuracy: 0.2366 - loss: 2.3647[32m [repeated 238x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m39s[0m 60ms/step - accuracy: 0.2547 - loss: 2.2560
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m39s[0m 60ms/step - accuracy: 0.2547 - loss: 2.2559[32m [repeated 197x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m330/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 46ms/step - accuracy: 0.2288 - loss: 2.3460
[1m331/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 46ms/step - accuracy: 0.2288 - loss: 2.3461
[1m332/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 46ms/step - accuracy: 0.2288 - loss: 2.3461
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m184/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 54ms/step - accuracy: 0.2008 - loss: 2.4463
[1m185/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 54ms/step - accuracy: 0.2009 - loss: 2.4463[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m347/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 46ms/step - accuracy: 0.2289 - loss: 2.3461[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m38s[0m 60ms/step - accuracy: 0.2549 - loss: 2.2555
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m38s[0m 60ms/step - accuracy: 0.2549 - loss: 2.2554
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m38s[0m 60ms/step - accuracy: 0.2549 - loss: 2.2554
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m60s[0m 52ms/step - accuracy: 0.1985 - loss: 2.5023 - val_accuracy: 0.2722 - val_loss: 2.3026
[36m(train_cnn_ray_tune pid=2697885)[0m Epoch 4/25
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 30ms/step - accuracy: 0.1744 - loss: 2.5577
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 30ms/step - accuracy: 0.1744 - loss: 2.5577[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 30ms/step - accuracy: 0.1744 - loss: 2.5576[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m63s[0m 55ms/step - accuracy: 0.1867 - loss: 2.6001 - val_accuracy: 0.2442 - val_loss: 2.2429
[36m(train_cnn_ray_tune pid=2697835)[0m Epoch 4/16
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.3125 - loss: 2.2646 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 47ms/step - accuracy: 0.2669 - loss: 2.3512 
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.2640 - loss: 2.3266 
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.2630 - loss: 2.3294
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:28[0m 129ms/step - accuracy: 0.3125 - loss: 2.6947[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2500 - loss: 2.8057 
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 46ms/step - accuracy: 0.2396 - loss: 2.8010 
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m437/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 45ms/step - accuracy: 0.2295 - loss: 2.3469
[1m439/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 45ms/step - accuracy: 0.2295 - loss: 2.3470[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 52ms/step - accuracy: 0.1619 - loss: 2.7913[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m41s[0m 63ms/step - accuracy: 0.2364 - loss: 2.3618[32m [repeated 298x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m31s[0m 35ms/step - accuracy: 0.1504 - loss: 2.7126
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m31s[0m 35ms/step - accuracy: 0.1504 - loss: 2.7128[32m [repeated 220x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m334/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.1807 - loss: 2.5372
[1m335/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.1807 - loss: 2.5371[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m277/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 54ms/step - accuracy: 0.2037 - loss: 2.4402[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.2065 - loss: 2.4210
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.2066 - loss: 2.4210
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.2066 - loss: 2.4210
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 47ms/step - accuracy: 0.0984 - loss: 3.0736
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 47ms/step - accuracy: 0.0984 - loss: 3.0736[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 47ms/step - accuracy: 0.0985 - loss: 3.0734[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m293/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.2041 - loss: 2.4390
[1m294/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.2042 - loss: 2.4389
[1m295/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.2042 - loss: 2.4388
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m77s[0m 44ms/step - accuracy: 0.1781 - loss: 2.7048 - val_accuracy: 0.2551 - val_loss: 2.3257
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 4/27
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m63s[0m 54ms/step - accuracy: 0.2001 - loss: 2.5184 - val_accuracy: 0.2922 - val_loss: 2.2137
[36m(train_cnn_ray_tune pid=2697862)[0m Epoch 4/27
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 43ms/step - accuracy: 0.2153 - loss: 2.3605  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 41ms/step - accuracy: 0.2042 - loss: 2.3645
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 47ms/step - accuracy: 0.0986 - loss: 3.0728
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 47ms/step - accuracy: 0.0986 - loss: 3.0727
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 47ms/step - accuracy: 0.0986 - loss: 3.0727
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2069 - loss: 2.4199 
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2069 - loss: 2.4199
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 47ms/step - accuracy: 0.0987 - loss: 3.0724
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 47ms/step - accuracy: 0.0987 - loss: 3.0724
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 47ms/step - accuracy: 0.0987 - loss: 3.0724
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:32[0m 133ms/step - accuracy: 0.2500 - loss: 2.2795
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m558/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 53ms/step - accuracy: 0.1627 - loss: 2.7892
[1m559/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 53ms/step - accuracy: 0.1627 - loss: 2.7892[32m [repeated 108x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:57[0m 101ms/step - accuracy: 0.1250 - loss: 2.6190
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 18ms/step - accuracy: 0.1585 - loss: 2.6065  
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m567/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.2392 - loss: 2.2976[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m21s[0m 44ms/step - accuracy: 0.1307 - loss: 2.8472[32m [repeated 275x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m27s[0m 36ms/step - accuracy: 0.1527 - loss: 2.7173
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m27s[0m 36ms/step - accuracy: 0.1527 - loss: 2.7173[32m [repeated 243x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m364/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 54ms/step - accuracy: 0.2059 - loss: 2.4336
[1m365/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 54ms/step - accuracy: 0.2059 - loss: 2.4335[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m366/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 54ms/step - accuracy: 0.2060 - loss: 2.4335[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 47ms/step - accuracy: 0.0989 - loss: 3.0717
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 47ms/step - accuracy: 0.0989 - loss: 3.0717[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 47ms/step - accuracy: 0.0989 - loss: 3.0715[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.2525 - loss: 2.2545 - val_accuracy: 0.3254 - val_loss: 2.1558
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 123ms/step - accuracy: 0.2188 - loss: 2.2177
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 34ms/step - accuracy: 0.1745 - loss: 2.5563 - val_accuracy: 0.2404 - val_loss: 2.3110
[36m(train_cnn_ray_tune pid=2697881)[0m Epoch 10/20[32m [repeated 2x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-07 12:43:51. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 57ms/step - accuracy: 0.2266 - loss: 2.3397  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 46ms/step - accuracy: 0.2546 - loss: 2.3125
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m431/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 55ms/step - accuracy: 0.2072 - loss: 2.4289
[1m432/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 55ms/step - accuracy: 0.2072 - loss: 2.4289[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 138ms/step - accuracy: 0.2188 - loss: 2.5458
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 61ms/step - accuracy: 0.1797 - loss: 2.7113  
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m534/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.1820 - loss: 2.5315[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 50ms/step - accuracy: 0.1883 - loss: 2.5169[32m [repeated 327x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m22s[0m 36ms/step - accuracy: 0.1547 - loss: 2.7150
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m22s[0m 37ms/step - accuracy: 0.1547 - loss: 2.7150[32m [repeated 210x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 23/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 59ms/step - accuracy: 0.1646 - loss: 2.7780
[1m 24/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 59ms/step - accuracy: 0.1646 - loss: 2.7795[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 38/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 43ms/step - accuracy: 0.2483 - loss: 2.2865[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 33ms/step - accuracy: 0.2069 - loss: 2.4186
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 33ms/step - accuracy: 0.2069 - loss: 2.4186[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 41ms/step - accuracy: 0.2674 - loss: 2.2324[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 59ms/step - accuracy: 0.1629 - loss: 2.7887 - val_accuracy: 0.2257 - val_loss: 2.4334[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47[0m 185ms/step - accuracy: 0.2188 - loss: 2.2970[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 7/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m35s[0m 43ms/step - accuracy: 0.1967 - loss: 2.6399
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m35s[0m 43ms/step - accuracy: 0.1966 - loss: 2.6400
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m35s[0m 43ms/step - accuracy: 0.1966 - loss: 2.6400
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m521/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 55ms/step - accuracy: 0.2088 - loss: 2.4231
[1m523/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 55ms/step - accuracy: 0.2089 - loss: 2.4230[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m525/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 55ms/step - accuracy: 0.2089 - loss: 2.4229[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 98ms/step - accuracy: 0.0625 - loss: 2.8308
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 54ms/step - accuracy: 0.0703 - loss: 2.8001
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m26s[0m 63ms/step - accuracy: 0.2362 - loss: 2.3564[32m [repeated 286x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.1558 - loss: 2.7133
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.1558 - loss: 2.7133[32m [repeated 230x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m125/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.1752 - loss: 2.7474
[1m126/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.1753 - loss: 2.7472[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 14/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 56ms/step - accuracy: 0.1479 - loss: 2.5749[32m [repeated 129x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 58ms/step - accuracy: 0.1942 - loss: 2.4861
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 58ms/step - accuracy: 0.1942 - loss: 2.4861[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m555/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 55ms/step - accuracy: 0.2094 - loss: 2.4214
[1m556/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 55ms/step - accuracy: 0.2094 - loss: 2.4213
[1m557/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 55ms/step - accuracy: 0.2094 - loss: 2.4213
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m279/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2544 - loss: 2.2470 
[1m281/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2544 - loss: 2.2470
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 58ms/step - accuracy: 0.1943 - loss: 2.4859[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 52ms/step - accuracy: 0.1823 - loss: 2.5305 - val_accuracy: 0.2601 - val_loss: 2.2856
[36m(train_cnn_ray_tune pid=2697882)[0m Epoch 8/16
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 37ms/step - accuracy: 0.2068 - loss: 2.4184 - val_accuracy: 0.2563 - val_loss: 2.2421
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 6/24
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 58ms/step - accuracy: 0.1945 - loss: 2.4853
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 58ms/step - accuracy: 0.1945 - loss: 2.4853
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 58ms/step - accuracy: 0.1945 - loss: 2.4853
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:29[0m 130ms/step - accuracy: 0.2500 - loss: 2.0214
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.2344 - loss: 2.0532  
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 47ms/step - accuracy: 0.2357 - loss: 2.0867
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m375/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.2543 - loss: 2.2467
[1m377/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.2543 - loss: 2.2467[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m383/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 33ms/step - accuracy: 0.2543 - loss: 2.2466[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:48[0m 94ms/step - accuracy: 0.1250 - loss: 2.8118
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.1181 - loss: 2.6873 
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:48[0m 94ms/step - accuracy: 0.1875 - loss: 2.5586
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1719 - loss: 2.6348
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m21s[0m 62ms/step - accuracy: 0.2363 - loss: 2.3549[32m [repeated 225x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 36ms/step - accuracy: 0.1569 - loss: 2.7113
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 36ms/step - accuracy: 0.1569 - loss: 2.7113[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 47ms/step - accuracy: 0.1667 - loss: 2.6746 
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m223/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 51ms/step - accuracy: 0.1791 - loss: 2.7407
[1m224/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 52ms/step - accuracy: 0.1791 - loss: 2.7406[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m131/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 44ms/step - accuracy: 0.1790 - loss: 2.5057[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m3s[0m 58ms/step - accuracy: 0.1947 - loss: 2.4847
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m3s[0m 58ms/step - accuracy: 0.1947 - loss: 2.4847[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 43ms/step - accuracy: 0.1359 - loss: 2.8322[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 62ms/step - accuracy: 0.2097 - loss: 2.4202 - val_accuracy: 0.2680 - val_loss: 2.2495
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m87s[0m 56ms/step - accuracy: 0.0991 - loss: 3.0704 - val_accuracy: 0.1662 - val_loss: 2.6391[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 7/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m345/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.2354 - loss: 2.3199 
[1m347/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.2354 - loss: 2.3199
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m524/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 33ms/step - accuracy: 0.2542 - loss: 2.2465
[1m526/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 33ms/step - accuracy: 0.2542 - loss: 2.2465[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 203/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 36ms/step - accuracy: 0.1894 - loss: 2.4113
[1m 204/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 36ms/step - accuracy: 0.1894 - loss: 2.4113
[1m 205/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m34s[0m 36ms/step - accuracy: 0.1895 - loss: 2.4112
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.1578 - loss: 2.7093
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.1578 - loss: 2.7093
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.1578 - loss: 2.7092
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m418/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 40ms/step - accuracy: 0.2455 - loss: 2.2743[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 135ms/step - accuracy: 0.1562 - loss: 2.6348
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 83ms/step - accuracy: 0.1562 - loss: 2.5909  
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m16s[0m 63ms/step - accuracy: 0.2365 - loss: 2.3535[32m [repeated 260x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 36ms/step - accuracy: 0.1902 - loss: 2.4104
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 36ms/step - accuracy: 0.1903 - loss: 2.4102[32m [repeated 217x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 76/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 54ms/step - accuracy: 0.2101 - loss: 2.4001
[1m 77/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 54ms/step - accuracy: 0.2101 - loss: 2.4001[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m315/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.1808 - loss: 2.7351[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m320/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.1808 - loss: 2.7348
[1m321/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.1809 - loss: 2.7347
[1m322/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.1809 - loss: 2.7346
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 36ms/step - accuracy: 0.1580 - loss: 2.7087
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 36ms/step - accuracy: 0.1580 - loss: 2.7086[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 60ms/step - accuracy: 0.2599 - loss: 2.2393[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.2539 - loss: 2.2463 - val_accuracy: 0.3192 - val_loss: 2.1690
[36m(train_cnn_ray_tune pid=2697881)[0m Epoch 11/20
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 110ms/step - accuracy: 0.3125 - loss: 2.2211
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m535/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.2452 - loss: 2.2740
[1m536/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.2452 - loss: 2.2740[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 60ms/step - accuracy: 0.2602 - loss: 2.2385
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 60ms/step - accuracy: 0.2602 - loss: 2.2384
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 60ms/step - accuracy: 0.2602 - loss: 2.2384
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m398/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 53ms/step - accuracy: 0.1815 - loss: 2.7317[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m10s[0m 62ms/step - accuracy: 0.2367 - loss: 2.3518[32m [repeated 232x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m28s[0m 49ms/step - accuracy: 0.2147 - loss: 2.4495
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m28s[0m 49ms/step - accuracy: 0.2147 - loss: 2.4494[32m [repeated 201x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1950 - loss: 2.4053
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1951 - loss: 2.4052
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1952 - loss: 2.4052
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1813 - loss: 2.5203 
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1813 - loss: 2.5203
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 57/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2296 - loss: 2.2738
[1m 59/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 33ms/step - accuracy: 0.2299 - loss: 2.2740[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m173/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 53ms/step - accuracy: 0.2105 - loss: 2.3976[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 48/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 33ms/step - accuracy: 0.2283 - loss: 2.2728
[1m 50/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 33ms/step - accuracy: 0.2286 - loss: 2.2730
[1m 52/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 33ms/step - accuracy: 0.2289 - loss: 2.2733
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 62ms/step - accuracy: 0.2368 - loss: 2.3515
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 62ms/step - accuracy: 0.2368 - loss: 2.3515[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m55s[0m 48ms/step - accuracy: 0.1370 - loss: 2.8290 - val_accuracy: 0.2464 - val_loss: 2.3629
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1813 - loss: 2.5200[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 42ms/step - accuracy: 0.0625 - loss: 2.6915  
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2083 - loss: 2.5346
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.2281 - loss: 2.5012 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 47ms/step - accuracy: 0.2288 - loss: 2.4811
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m217/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 52ms/step - accuracy: 0.2106 - loss: 2.3958
[1m218/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 52ms/step - accuracy: 0.2106 - loss: 2.3957
[1m219/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 52ms/step - accuracy: 0.2106 - loss: 2.3956
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.2817 - loss: 2.3226
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.2779 - loss: 2.3289
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.2691 - loss: 2.3389
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.2658 - loss: 2.3422
[36m(train_cnn_ray_tune pid=2697817)[0m Epoch 4/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:18[0m 120ms/step - accuracy: 0.3125 - loss: 2.2842[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 44ms/step - accuracy: 0.2452 - loss: 2.2739 - val_accuracy: 0.2889 - val_loss: 2.2539
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2573 - loss: 2.3491
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2555 - loss: 2.3491
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 50ms/step - accuracy: 0.2882 - loss: 2.1797  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 53ms/step - accuracy: 0.2747 - loss: 2.1816
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.2537 - loss: 2.3499
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.2521 - loss: 2.3503
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.2473 - loss: 2.3518
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.2460 - loss: 2.3524
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.2443 - loss: 2.3531
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.2438 - loss: 2.3527
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m458/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 43ms/step - accuracy: 0.1863 - loss: 2.4996
[1m460/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 43ms/step - accuracy: 0.1863 - loss: 2.4996[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.2431 - loss: 2.3512
[1m  31/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.2427 - loss: 2.3513
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m495/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 52ms/step - accuracy: 0.1815 - loss: 2.7306[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  37/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2400 - loss: 2.3527
[1m  38/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2394 - loss: 2.3530
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  39/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.2389 - loss: 2.3533
[1m  40/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.2385 - loss: 2.3535
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m37s[0m 45ms/step - accuracy: 0.1072 - loss: 3.0169[32m [repeated 237x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 33ms/step - accuracy: 0.1983 - loss: 2.4025
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 33ms/step - accuracy: 0.1983 - loss: 2.4025[32m [repeated 168x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m16s[0m 49ms/step - accuracy: 0.2080 - loss: 2.4363
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m16s[0m 49ms/step - accuracy: 0.2080 - loss: 2.4363
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m15s[0m 49ms/step - accuracy: 0.2080 - loss: 2.4363[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.2353 - loss: 2.3557
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.2351 - loss: 2.3559
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 46/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2510 - loss: 2.2469
[1m 48/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2504 - loss: 2.2484[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m271/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 52ms/step - accuracy: 0.2113 - loss: 2.3929[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.2349 - loss: 2.3562
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2346 - loss: 2.3565
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2337 - loss: 2.3574
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 54ms/step - accuracy: 0.2332 - loss: 2.3580 
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 31ms/step - accuracy: 0.1817 - loss: 2.5180
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 31ms/step - accuracy: 0.1817 - loss: 2.5180[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m75s[0m 65ms/step - accuracy: 0.1950 - loss: 2.4839 - val_accuracy: 0.2658 - val_loss: 2.2604[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 62ms/step - accuracy: 0.2370 - loss: 2.3499[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.3125 - loss: 2.2856 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  65/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2314 - loss: 2.3604
[1m  66/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2311 - loss: 2.3607
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.1719 - loss: 2.5383 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.2253 - loss: 2.4515 
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  63/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2320 - loss: 2.3598[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  67/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 55ms/step - accuracy: 0.2309 - loss: 2.3611 
[1m  69/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 55ms/step - accuracy: 0.2303 - loss: 2.3618
Trial status: 20 RUNNING
Current time: 2025-11-07 12:44:21. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 9/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:18[0m 120ms/step - accuracy: 0.1250 - loss: 2.6102[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 52ms/step - accuracy: 0.2370 - loss: 2.3160 - val_accuracy: 0.2712 - val_loss: 2.2372
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 53ms/step - accuracy: 0.1736 - loss: 2.3957  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 48ms/step - accuracy: 0.1829 - loss: 2.3873
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m339/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.2478 - loss: 2.2597
[1m341/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.2479 - loss: 2.2596[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m358/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.2483 - loss: 2.2589[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 34ms/step - accuracy: 0.1939 - loss: 2.6486[32m [repeated 281x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m32s[0m 45ms/step - accuracy: 0.1072 - loss: 3.0196
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m32s[0m 45ms/step - accuracy: 0.1072 - loss: 3.0196[32m [repeated 192x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 176/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m40s[0m 41ms/step - accuracy: 0.2116 - loss: 2.4221
[1m 177/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m40s[0m 42ms/step - accuracy: 0.2116 - loss: 2.4221
[1m 178/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m40s[0m 42ms/step - accuracy: 0.2115 - loss: 2.4222
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m372/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 52ms/step - accuracy: 0.2131 - loss: 2.3879
[1m373/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 52ms/step - accuracy: 0.2131 - loss: 2.3879[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m179/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m15s[0m 38ms/step - accuracy: 0.2456 - loss: 2.2689[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2083 - loss: 2.4345
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2083 - loss: 2.4345[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m383/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2132 - loss: 2.3874 
[1m384/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2133 - loss: 2.3874
[1m385/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2133 - loss: 2.3874
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m46s[0m 40ms/step - accuracy: 0.1591 - loss: 2.7049 - val_accuracy: 0.2172 - val_loss: 2.3272
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m77s[0m 67ms/step - accuracy: 0.2608 - loss: 2.2363 - val_accuracy: 0.3361 - val_loss: 2.1166
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2083 - loss: 2.4344[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.5781 - loss: 1.7024 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.5382 - loss: 1.7585
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2083 - loss: 2.4343
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2083 - loss: 2.4343
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2083 - loss: 2.4343
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 47ms/step - accuracy: 0.1867 - loss: 2.4984 - val_accuracy: 0.2623 - val_loss: 2.2763
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.4562 - loss: 1.8787
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.4431 - loss: 1.9018
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2105 - loss: 2.5095 
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2105 - loss: 2.5095
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.4333 - loss: 1.9189
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.4256 - loss: 1.9303
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.4048 - loss: 1.9641
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.3988 - loss: 1.9772
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.3778 - loss: 2.0177
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.3740 - loss: 2.0247
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.3873 - loss: 2.0004[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.3710 - loss: 2.0306
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.3680 - loss: 2.0367
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.3654 - loss: 2.0415
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.3630 - loss: 2.0460
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.3521 - loss: 2.0638
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.3482 - loss: 2.0691
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  31/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.3465 - loss: 2.0713
[1m  32/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.3447 - loss: 2.0733
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  33/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3431 - loss: 2.0750
[1m  35/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3404 - loss: 2.0775
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  38/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3363 - loss: 2.0821
[1m  39/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3349 - loss: 2.0839
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  40/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3336 - loss: 2.0857
[1m  41/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3325 - loss: 2.0870
[36m(train_cnn_ray_tune pid=2697874)[0m Epoch 7/18[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 112ms/step - accuracy: 0.1562 - loss: 2.6685[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  45/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3280 - loss: 2.0937
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3270 - loss: 2.0955
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.2465 - loss: 2.3636 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.2435 - loss: 2.3666
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.1719 - loss: 2.5710  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.1703 - loss: 2.5687
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3227 - loss: 2.1031
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3219 - loss: 2.1046
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.3195 - loss: 2.1092
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.3189 - loss: 2.1104
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m449/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2140 - loss: 2.3851
[1m451/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2140 - loss: 2.3851[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.3184 - loss: 2.1114
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.3179 - loss: 2.1123
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  63/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.3161 - loss: 2.1156
[1m  64/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.3157 - loss: 2.1163
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  65/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.3152 - loss: 2.1169
[1m  66/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.3148 - loss: 2.1176
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m458/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2141 - loss: 2.3849[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  70/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.3133 - loss: 2.1203
[1m  71/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.3130 - loss: 2.1208
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m31s[0m 39ms/step - accuracy: 0.1474 - loss: 2.7982[32m [repeated 206x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.2175 - loss: 2.4385
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.2175 - loss: 2.4385[32m [repeated 191x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  74/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.3121 - loss: 2.1225
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.3118 - loss: 2.1230
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 99/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.1746 - loss: 2.5383
[1m101/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.1748 - loss: 2.5375[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m102/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.1749 - loss: 2.5371[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.3109 - loss: 2.1243
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.3107 - loss: 2.1246
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m318/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2476 - loss: 2.2663 
[1m320/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2476 - loss: 2.2662
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.2019 - loss: 2.3978
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.2020 - loss: 2.3977[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 34ms/step - accuracy: 0.1818 - loss: 2.5168 - val_accuracy: 0.2567 - val_loss: 2.2784
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.2020 - loss: 2.3976[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 57ms/step - accuracy: 0.1813 - loss: 2.7298 - val_accuracy: 0.2339 - val_loss: 2.3994
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.3101 - loss: 2.1255[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m79s[0m 68ms/step - accuracy: 0.2372 - loss: 2.3486 - val_accuracy: 0.3079 - val_loss: 2.1584
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 67ms/step - accuracy: 0.5781 - loss: 1.9243 
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 67ms/step - accuracy: 0.4229 - loss: 2.1714
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.4071 - loss: 2.1851
[36m(train_cnn_ray_tune pid=2697836)[0m Epoch 4/23
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:31[0m 131ms/step - accuracy: 0.6875 - loss: 1.7991[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 66ms/step - accuracy: 0.3726 - loss: 2.2188
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 67ms/step - accuracy: 0.3656 - loss: 2.2234
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 56ms/step - accuracy: 0.3095 - loss: 2.1264 
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 56ms/step - accuracy: 0.3092 - loss: 2.1268
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.3435 - loss: 2.2386
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3389 - loss: 2.2402
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 36ms/step - accuracy: 0.2509 - loss: 2.2519 - val_accuracy: 0.3190 - val_loss: 2.1646
[36m(train_cnn_ray_tune pid=2697881)[0m Epoch 12/20
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3354 - loss: 2.2404
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.3318 - loss: 2.2417
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 98ms/step - accuracy: 0.1250 - loss: 2.4754
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.1701 - loss: 2.3997
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.3284 - loss: 2.2424
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.3251 - loss: 2.2427
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.3225 - loss: 2.2422
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3197 - loss: 2.2421
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m545/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 51ms/step - accuracy: 0.2146 - loss: 2.3836
[1m546/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 51ms/step - accuracy: 0.2146 - loss: 2.3836[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.3100 - loss: 2.2414
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.3085 - loss: 2.2414
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3071 - loss: 2.2413
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3059 - loss: 2.2410
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  31/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.3045 - loss: 2.2408
[1m  32/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.3033 - loss: 2.2406
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m556/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 52ms/step - accuracy: 0.2147 - loss: 2.3835[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  33/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.3022 - loss: 2.2401
[1m  34/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.3009 - loss: 2.2402
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m22s[0m 32ms/step - accuracy: 0.1814 - loss: 2.6429[32m [repeated 208x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m22s[0m 45ms/step - accuracy: 0.1071 - loss: 3.0168
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m22s[0m 45ms/step - accuracy: 0.1071 - loss: 3.0167[32m [repeated 180x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  38/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.2965 - loss: 2.2410
[1m  39/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.2956 - loss: 2.2416
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m205/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 43ms/step - accuracy: 0.1839 - loss: 2.5072
[1m206/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 43ms/step - accuracy: 0.1840 - loss: 2.5070[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m180/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 49ms/step - accuracy: 0.1880 - loss: 2.7044[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 31ms/step - accuracy: 0.2028 - loss: 2.3962
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 31ms/step - accuracy: 0.2028 - loss: 2.3962[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.2877 - loss: 2.2481
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.2870 - loss: 2.2490
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 47ms/step - accuracy: 0.2182 - loss: 2.4358[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2829 - loss: 2.2539
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 62ms/step - accuracy: 0.2825 - loss: 2.2543
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  60/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 62ms/step - accuracy: 0.2821 - loss: 2.2547
[1m  61/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 62ms/step - accuracy: 0.2818 - loss: 2.2551
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m26s[0m 41ms/step - accuracy: 0.1484 - loss: 2.7930
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m26s[0m 41ms/step - accuracy: 0.1484 - loss: 2.7929
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m26s[0m 41ms/step - accuracy: 0.1484 - loss: 2.7929
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  67/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 61ms/step - accuracy: 0.2800 - loss: 2.2564
[1m  69/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2796 - loss: 2.2566
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  72/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2789 - loss: 2.2570[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 61ms/step - accuracy: 0.2781 - loss: 2.2575
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.2779 - loss: 2.2577
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2777 - loss: 2.2578
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 61ms/step - accuracy: 0.2775 - loss: 2.2579
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2773 - loss: 2.2580
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2771 - loss: 2.2582
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2769 - loss: 2.2583
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2768 - loss: 2.2584
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m55s[0m 47ms/step - accuracy: 0.1959 - loss: 2.6258 - val_accuracy: 0.2718 - val_loss: 2.2765
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2766 - loss: 2.2585
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.2765 - loss: 2.2586
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 5/27
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:07[0m 111ms/step - accuracy: 0.2500 - loss: 2.6658
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.2396 - loss: 2.6046  
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2731 - loss: 2.2606
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2730 - loss: 2.2607
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m552/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.2504 - loss: 2.2605
[1m553/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.2504 - loss: 2.2604[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 58ms/step - accuracy: 0.2149 - loss: 2.3830 - val_accuracy: 0.2696 - val_loss: 2.2445
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 8/28
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m62s[0m 53ms/step - accuracy: 0.2084 - loss: 2.4329 - val_accuracy: 0.2672 - val_loss: 2.2722
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:27[0m 76ms/step - accuracy: 0.1250 - loss: 2.4634
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2722 - loss: 2.2613
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2721 - loss: 2.2614
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m566/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.2505 - loss: 2.2602[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.1250 - loss: 2.4094 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 41ms/step - accuracy: 0.1367 - loss: 2.3984
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:33[0m 162ms/step - accuracy: 0.2812 - loss: 2.2328
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 49ms/step - accuracy: 0.2257 - loss: 2.2396  
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 117/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2720 - loss: 2.2615
[1m 118/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2719 - loss: 2.2615
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.1491 - loss: 2.7908[32m [repeated 231x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.1794 - loss: 2.6412
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.1794 - loss: 2.6412[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 120/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2717 - loss: 2.2616
[1m 121/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2716 - loss: 2.2616
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 122/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2716 - loss: 2.2616
[1m 123/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2715 - loss: 2.2616
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 10/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 58ms/step - accuracy: 0.2024 - loss: 2.2802
[1m 11/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 59ms/step - accuracy: 0.2029 - loss: 2.2808[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m276/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 50ms/step - accuracy: 0.1862 - loss: 2.7093[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 127/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 61ms/step - accuracy: 0.2713 - loss: 2.2615
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 61ms/step - accuracy: 0.2712 - loss: 2.2615
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 40ms/step - accuracy: 0.2787 - loss: 2.1891
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 40ms/step - accuracy: 0.2787 - loss: 2.1891[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1774 - loss: 2.3667 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1789 - loss: 2.3669
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 48ms/step - accuracy: 0.2186 - loss: 2.4339[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m353/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.1901 - loss: 2.4907 
[1m355/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.1901 - loss: 2.4906
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1953 - loss: 2.3714[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 54ms/step - accuracy: 0.1964 - loss: 2.3724 
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1967 - loss: 2.3727
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.1979 - loss: 2.4120  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 65/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 54ms/step - accuracy: 0.2296 - loss: 2.2997
[1m 66/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 54ms/step - accuracy: 0.2296 - loss: 2.3001
[1m 67/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 54ms/step - accuracy: 0.2297 - loss: 2.3004
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.1785 - loss: 2.6408
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.1785 - loss: 2.6408
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 33ms/step - accuracy: 0.1785 - loss: 2.6408
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.2698 - loss: 2.2614
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 60ms/step - accuracy: 0.2697 - loss: 2.2614 [32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m505/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 41ms/step - accuracy: 0.2522 - loss: 2.2708
[1m506/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 41ms/step - accuracy: 0.2522 - loss: 2.2708[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.2506 - loss: 2.2600 - val_accuracy: 0.2901 - val_loss: 2.2257
[36m(train_cnn_ray_tune pid=2697828)[0m Epoch 11/27[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m61s[0m 53ms/step - accuracy: 0.2096 - loss: 2.5097 - val_accuracy: 0.2575 - val_loss: 2.2223[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:02[0m 159ms/step - accuracy: 0.0625 - loss: 2.6313
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m515/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 42ms/step - accuracy: 0.2522 - loss: 2.2709[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 131ms/step - accuracy: 0.2188 - loss: 2.1642
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 51ms/step - accuracy: 0.2031 - loss: 2.2181  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 201/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m58s[0m 61ms/step - accuracy: 0.2684 - loss: 2.2613[32m [repeated 274x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.1783 - loss: 2.6407
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.1783 - loss: 2.6407[32m [repeated 211x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m368/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 51ms/step - accuracy: 0.1849 - loss: 2.7094
[1m369/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 51ms/step - accuracy: 0.1849 - loss: 2.7094[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m367/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 51ms/step - accuracy: 0.1849 - loss: 2.7094[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 40ms/step - accuracy: 0.2792 - loss: 2.1878
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 40ms/step - accuracy: 0.2792 - loss: 2.1878[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 40ms/step - accuracy: 0.2792 - loss: 2.1877[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 54ms/step - accuracy: 0.1986 - loss: 2.3770 [32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m477/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 45ms/step - accuracy: 0.1922 - loss: 2.4851
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 45ms/step - accuracy: 0.1922 - loss: 2.4851
[1m479/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 45ms/step - accuracy: 0.1922 - loss: 2.4850
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.1080 - loss: 3.0107 
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.1080 - loss: 3.0107
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m10s[0m 46ms/step - accuracy: 0.1080 - loss: 3.0110
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m10s[0m 46ms/step - accuracy: 0.1080 - loss: 3.0110
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m10s[0m 47ms/step - accuracy: 0.1080 - loss: 3.0109[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m501/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 46ms/step - accuracy: 0.1925 - loss: 2.4841
[1m503/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 46ms/step - accuracy: 0.1925 - loss: 2.4840[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m Epoch 5/27
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m62s[0m 53ms/step - accuracy: 0.2186 - loss: 2.4338 - val_accuracy: 0.2968 - val_loss: 2.1780
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m181/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 55ms/step - accuracy: 0.2282 - loss: 2.3213
[1m182/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 55ms/step - accuracy: 0.2282 - loss: 2.3214
[1m183/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 55ms/step - accuracy: 0.2282 - loss: 2.3215
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m511/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 46ms/step - accuracy: 0.1926 - loss: 2.4837[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:23[0m 125ms/step - accuracy: 0.1875 - loss: 2.4254
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 45ms/step - accuracy: 0.2014 - loss: 2.3575  
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m16s[0m 43ms/step - accuracy: 0.2102 - loss: 2.4298[32m [repeated 250x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.1776 - loss: 2.6407
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.1776 - loss: 2.6407[32m [repeated 300x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m191/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 55ms/step - accuracy: 0.2281 - loss: 2.3222
[1m192/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 55ms/step - accuracy: 0.2281 - loss: 2.3222[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m194/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 56ms/step - accuracy: 0.2281 - loss: 2.3224[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 47ms/step - accuracy: 0.2522 - loss: 2.2715 - val_accuracy: 0.2934 - val_loss: 2.2095
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 10/27
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 120ms/step - accuracy: 0.2500 - loss: 2.0725
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 47ms/step - accuracy: 0.1082 - loss: 3.0098
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 47ms/step - accuracy: 0.1082 - loss: 3.0098[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 47ms/step - accuracy: 0.1082 - loss: 3.0097[32m [repeated 51x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-07 12:44:51. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m225/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 56ms/step - accuracy: 0.2279 - loss: 2.3247
[1m226/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 57ms/step - accuracy: 0.2279 - loss: 2.3248
[1m227/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 56ms/step - accuracy: 0.2279 - loss: 2.3248
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.1512 - loss: 2.7816 
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.1512 - loss: 2.7815
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m530/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 52ms/step - accuracy: 0.1838 - loss: 2.7075
[1m531/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 52ms/step - accuracy: 0.1838 - loss: 2.7075[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 48ms/step - accuracy: 0.2266 - loss: 2.3725
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 48ms/step - accuracy: 0.2265 - loss: 2.3727
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 48ms/step - accuracy: 0.2265 - loss: 2.3729
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m543/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 52ms/step - accuracy: 0.1838 - loss: 2.7073[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m271/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 56ms/step - accuracy: 0.2280 - loss: 2.3263
[1m272/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 56ms/step - accuracy: 0.2280 - loss: 2.3263
[1m273/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 56ms/step - accuracy: 0.2280 - loss: 2.3263
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m49s[0m 62ms/step - accuracy: 0.2641 - loss: 2.2686[32m [repeated 282x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.2150 - loss: 2.3650
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.2150 - loss: 2.3650[32m [repeated 234x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m52s[0m 45ms/step - accuracy: 0.2798 - loss: 2.1865 - val_accuracy: 0.3317 - val_loss: 2.0540
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m103/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m21s[0m 45ms/step - accuracy: 0.2553 - loss: 2.2394
[1m104/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m21s[0m 45ms/step - accuracy: 0.2553 - loss: 2.2396[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m282/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 56ms/step - accuracy: 0.2281 - loss: 2.3265[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 42ms/step - accuracy: 0.1979 - loss: 2.4085 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 39ms/step - accuracy: 0.2294 - loss: 2.3486
[36m(train_cnn_ray_tune pid=2697873)[0m Epoch 6/28
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.2611 - loss: 2.2289 - val_accuracy: 0.3286 - val_loss: 2.1415
[36m(train_cnn_ray_tune pid=2697881)[0m Epoch 13/20
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 97ms/step - accuracy: 0.1875 - loss: 2.1564[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 118ms/step - accuracy: 0.2188 - loss: 2.5834
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.1953 - loss: 2.5760  
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.1086 - loss: 3.0081
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 47ms/step - accuracy: 0.1086 - loss: 3.0081
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 47ms/step - accuracy: 0.1086 - loss: 3.0081
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 34ms/step - accuracy: 0.1769 - loss: 2.6404
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 34ms/step - accuracy: 0.1769 - loss: 2.6404[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 47ms/step - accuracy: 0.1086 - loss: 3.0080[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m298/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 56ms/step - accuracy: 0.2282 - loss: 2.3270
[1m299/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 56ms/step - accuracy: 0.2282 - loss: 2.3271
[1m300/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 56ms/step - accuracy: 0.2282 - loss: 2.3271
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1888 - loss: 2.4810 
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1888 - loss: 2.4810
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m413/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 38ms/step - accuracy: 0.2607 - loss: 2.2089
[1m415/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 38ms/step - accuracy: 0.2607 - loss: 2.2089[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m39s[0m 49ms/step - accuracy: 0.2126 - loss: 2.4031
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m39s[0m 49ms/step - accuracy: 0.2126 - loss: 2.4031
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m39s[0m 49ms/step - accuracy: 0.2126 - loss: 2.4030
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m442/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 38ms/step - accuracy: 0.2606 - loss: 2.2095[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m45s[0m 63ms/step - accuracy: 0.2628 - loss: 2.2698[32m [repeated 275x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 33ms/step - accuracy: 0.2161 - loss: 2.3640
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 33ms/step - accuracy: 0.2161 - loss: 2.3640[32m [repeated 184x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m370/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 56ms/step - accuracy: 0.2284 - loss: 2.3283
[1m371/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 56ms/step - accuracy: 0.2284 - loss: 2.3283[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m102/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 46ms/step - accuracy: 0.2067 - loss: 2.4603[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 46ms/step - accuracy: 0.1684 - loss: 2.7830  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 53ms/step - accuracy: 0.1732 - loss: 2.7839
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 59ms/step - accuracy: 0.1837 - loss: 2.7066 - val_accuracy: 0.2426 - val_loss: 2.3743[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 9/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:20[0m 139ms/step - accuracy: 0.1562 - loss: 2.9122
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.1521 - loss: 2.7784
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.1521 - loss: 2.7784[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m38s[0m 49ms/step - accuracy: 0.2090 - loss: 2.5084
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m38s[0m 49ms/step - accuracy: 0.2090 - loss: 2.5083
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m38s[0m 49ms/step - accuracy: 0.2090 - loss: 2.5082
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.1522 - loss: 2.7783[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 32ms/step - accuracy: 0.1887 - loss: 2.4799
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 32ms/step - accuracy: 0.1887 - loss: 2.4799
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 32ms/step - accuracy: 0.1887 - loss: 2.4798
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 55/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 55ms/step - accuracy: 0.1786 - loss: 2.7342
[1m 56/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 55ms/step - accuracy: 0.1787 - loss: 2.7337
[1m 57/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 55ms/step - accuracy: 0.1787 - loss: 2.7332
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m552/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 39ms/step - accuracy: 0.2604 - loss: 2.2114
[1m554/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.2604 - loss: 2.2114[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m566/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 39ms/step - accuracy: 0.2604 - loss: 2.2116[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m18s[0m 57ms/step - accuracy: 0.2149 - loss: 2.4117[32m [repeated 252x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m40s[0m 63ms/step - accuracy: 0.2616 - loss: 2.2704
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m40s[0m 63ms/step - accuracy: 0.2616 - loss: 2.2704[32m [repeated 193x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m44s[0m 38ms/step - accuracy: 0.1764 - loss: 2.6399 - val_accuracy: 0.2226 - val_loss: 2.3168
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:02[0m 106ms/step - accuracy: 0.1250 - loss: 2.7301
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 52ms/step - accuracy: 0.1250 - loss: 2.7922 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 41ms/step - accuracy: 0.1276 - loss: 2.8115 
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m204/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 47ms/step - accuracy: 0.2042 - loss: 2.4517
[1m206/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 47ms/step - accuracy: 0.2042 - loss: 2.4517[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 94/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 53ms/step - accuracy: 0.1818 - loss: 2.7161[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m Epoch 5/17[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.2057 - loss: 3.0079
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.1971 - loss: 2.9981
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.2109 - loss: 2.4301
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.2109 - loss: 2.4301[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 36ms/step - accuracy: 0.1686 - loss: 2.7004
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.1691 - loss: 2.6962
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.1693 - loss: 2.6926
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.1885 - loss: 2.9825
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.1833 - loss: 2.9600
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.1737 - loss: 2.9398
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.1695 - loss: 2.9303
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.2109 - loss: 2.4301[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  12/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.1616 - loss: 2.9200
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.1557 - loss: 2.9127
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1503 - loss: 2.9122
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1480 - loss: 2.9125
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1443 - loss: 2.9115
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1430 - loss: 2.9109
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1418 - loss: 2.9089
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.1415 - loss: 2.9080
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1414 - loss: 2.9076
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.1413 - loss: 2.9053 
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m27s[0m 48ms/step - accuracy: 0.2158 - loss: 2.3990
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m27s[0m 48ms/step - accuracy: 0.2158 - loss: 2.3989
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m27s[0m 48ms/step - accuracy: 0.2158 - loss: 2.3989
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.2604 - loss: 2.2118 - val_accuracy: 0.3198 - val_loss: 2.2279
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  44/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1425 - loss: 2.8973
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1429 - loss: 2.8973
[1m  47/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.1431 - loss: 2.8972
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 54ms/step - accuracy: 0.1434 - loss: 2.8972 
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 54ms/step - accuracy: 0.1435 - loss: 2.8972 
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m417/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 44ms/step - accuracy: 0.2529 - loss: 2.2529
[1m418/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 44ms/step - accuracy: 0.2529 - loss: 2.2529
[1m419/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 44ms/step - accuracy: 0.2529 - loss: 2.2529
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 69ms/step - accuracy: 0.0781 - loss: 2.9444 
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m536/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 56ms/step - accuracy: 0.2279 - loss: 2.3310
[1m537/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 56ms/step - accuracy: 0.2279 - loss: 2.3310[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:04[0m 108ms/step - accuracy: 0.0625 - loss: 2.7204
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1393 - loss: 2.6323  
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2176 - loss: 2.3609 
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2176 - loss: 2.3609
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m438/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 44ms/step - accuracy: 0.2529 - loss: 2.2528[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m25s[0m 48ms/step - accuracy: 0.2160 - loss: 2.3981[32m [repeated 266x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m35s[0m 63ms/step - accuracy: 0.2609 - loss: 2.2697
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m34s[0m 63ms/step - accuracy: 0.2609 - loss: 2.2697[32m [repeated 235x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 36ms/step - accuracy: 0.1887 - loss: 2.4792 - val_accuracy: 0.2704 - val_loss: 2.2649[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:18[0m 120ms/step - accuracy: 0.0625 - loss: 2.9460[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.2500 - loss: 3.0016 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.2222 - loss: 3.0127
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m24s[0m 48ms/step - accuracy: 0.2160 - loss: 2.3980
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m24s[0m 48ms/step - accuracy: 0.2160 - loss: 2.3980
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m24s[0m 48ms/step - accuracy: 0.2160 - loss: 2.3980
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m318/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 46ms/step - accuracy: 0.2031 - loss: 2.4511
[1m319/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 46ms/step - accuracy: 0.2031 - loss: 2.4511[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m190/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m20s[0m 53ms/step - accuracy: 0.1857 - loss: 2.6979[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m Epoch 8/18[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.1180 - loss: 2.9182
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1237 - loss: 2.9157
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.2178 - loss: 2.3605
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.2178 - loss: 2.3605[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.2178 - loss: 2.3604[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.1277 - loss: 2.9069 [32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m35s[0m 51ms/step - accuracy: 0.2236 - loss: 2.3822
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m35s[0m 51ms/step - accuracy: 0.2236 - loss: 2.3822
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m35s[0m 51ms/step - accuracy: 0.2236 - loss: 2.3822
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.1806 - loss: 2.6133  
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.1745 - loss: 2.5874
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m21s[0m 60ms/step - accuracy: 0.2858 - loss: 2.1521
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m21s[0m 60ms/step - accuracy: 0.2858 - loss: 2.1521
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m21s[0m 60ms/step - accuracy: 0.2858 - loss: 2.1521
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m539/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 35ms/step - accuracy: 0.2658 - loss: 2.2002
[1m541/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 35ms/step - accuracy: 0.2658 - loss: 2.2002[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m405/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 47ms/step - accuracy: 0.2025 - loss: 2.4503[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m29s[0m 63ms/step - accuracy: 0.2605 - loss: 2.2685[32m [repeated 347x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 179/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m51s[0m 52ms/step - accuracy: 0.1304 - loss: 2.9301
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m51s[0m 52ms/step - accuracy: 0.1304 - loss: 2.9302[32m [repeated 242x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m56s[0m 49ms/step - accuracy: 0.2109 - loss: 2.4301 - val_accuracy: 0.2571 - val_loss: 2.2210
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:09[0m 113ms/step - accuracy: 0.1875 - loss: 2.6982
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 62ms/step - accuracy: 0.2279 - loss: 2.3312 - val_accuracy: 0.2809 - val_loss: 2.2321
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 159ms/step - accuracy: 0.2812 - loss: 2.1238
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m283/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 53ms/step - accuracy: 0.1874 - loss: 2.6916
[1m284/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 53ms/step - accuracy: 0.1875 - loss: 2.6915[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m193/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m15s[0m 39ms/step - accuracy: 0.2794 - loss: 2.1977[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 52ms/step - accuracy: 0.2951 - loss: 2.1309  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 55ms/step - accuracy: 0.2878 - loss: 2.1547
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 9/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 32ms/step - accuracy: 0.2182 - loss: 2.3593
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 32ms/step - accuracy: 0.2182 - loss: 2.3593[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.2020 - loss: 2.5676[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m17s[0m 60ms/step - accuracy: 0.2862 - loss: 2.1510
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m17s[0m 60ms/step - accuracy: 0.2862 - loss: 2.1510
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m17s[0m 60ms/step - accuracy: 0.2862 - loss: 2.1509
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 104ms/step - accuracy: 0.2500 - loss: 2.2422
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2708 - loss: 2.2270  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 67/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 59ms/step - accuracy: 0.2501 - loss: 2.2805
[1m 68/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 59ms/step - accuracy: 0.2499 - loss: 2.2808
[1m 69/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 58ms/step - accuracy: 0.2497 - loss: 2.2812
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m504/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2026 - loss: 2.4493
[1m505/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2026 - loss: 2.4493[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m514/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 47ms/step - accuracy: 0.2027 - loss: 2.4492[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m22s[0m 41ms/step - accuracy: 0.3036 - loss: 2.1230[32m [repeated 298x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m28s[0m 34ms/step - accuracy: 0.1935 - loss: 2.4634
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m28s[0m 34ms/step - accuracy: 0.1935 - loss: 2.4634[32m [repeated 229x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 49ms/step - accuracy: 0.2532 - loss: 2.2526 - val_accuracy: 0.2980 - val_loss: 2.2085[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 129ms/step - accuracy: 0.2500 - loss: 2.2398
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 89/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 57ms/step - accuracy: 0.2471 - loss: 2.2865
[1m 90/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 57ms/step - accuracy: 0.2470 - loss: 2.2867
[1m 91/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 57ms/step - accuracy: 0.2470 - loss: 2.2869
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 67/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 34ms/step - accuracy: 0.2810 - loss: 2.2271
[1m 71/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 33ms/step - accuracy: 0.2814 - loss: 2.2249[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 37/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 46ms/step - accuracy: 0.2641 - loss: 2.2433[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 61ms/step - accuracy: 0.2500 - loss: 2.2625  
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 56ms/step - accuracy: 0.2569 - loss: 2.2567
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 11/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 57ms/step - accuracy: 0.2151 - loss: 2.4115
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 57ms/step - accuracy: 0.2151 - loss: 2.4115[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 57ms/step - accuracy: 0.2151 - loss: 2.4115[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1934 - loss: 2.4613
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1934 - loss: 2.4612
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1934 - loss: 2.4612
Trial status: 20 RUNNING
Current time: 2025-11-07 12:45:22. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 36ms/step - accuracy: 0.2183 - loss: 2.3588 - val_accuracy: 0.2589 - val_loss: 2.2156
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46[0m 92ms/step - accuracy: 0.2500 - loss: 2.4380
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.2361 - loss: 2.4407 
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 61/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.2648 - loss: 2.2400
[1m 62/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.2648 - loss: 2.2399
[1m 63/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.2649 - loss: 2.2399[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m450/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 53ms/step - accuracy: 0.1888 - loss: 2.6830
[1m452/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 53ms/step - accuracy: 0.1888 - loss: 2.6829[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m463/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 53ms/step - accuracy: 0.1888 - loss: 2.6826[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m38s[0m 50ms/step - accuracy: 0.1283 - loss: 2.9376[32m [repeated 254x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m20s[0m 63ms/step - accuracy: 0.2599 - loss: 2.2669
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m20s[0m 63ms/step - accuracy: 0.2599 - loss: 2.2669[32m [repeated 255x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m184/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 55ms/step - accuracy: 0.2419 - loss: 2.3021
[1m185/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 55ms/step - accuracy: 0.2418 - loss: 2.3022[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m213/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.2799 - loss: 2.2062[32m [repeated 90x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 8/24
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 60ms/step - accuracy: 0.2867 - loss: 2.1492
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 60ms/step - accuracy: 0.2867 - loss: 2.1492[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.2165 - loss: 2.3946 
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.2165 - loss: 2.3946
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.2027 - loss: 2.4487 - val_accuracy: 0.2762 - val_loss: 2.2527
[36m(train_cnn_ray_tune pid=2697882)[0m Epoch 11/16
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 60ms/step - accuracy: 0.2867 - loss: 2.1492[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 136ms/step - accuracy: 0.2500 - loss: 2.0554
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m38s[0m 45ms/step - accuracy: 0.1488 - loss: 2.7625
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m38s[0m 45ms/step - accuracy: 0.1489 - loss: 2.7623
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m38s[0m 45ms/step - accuracy: 0.1489 - loss: 2.7622
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.1762 - loss: 2.6114
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.1762 - loss: 2.6114
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.1761 - loss: 2.6114
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m253/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.2397 - loss: 2.3065
[1m254/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.2397 - loss: 2.3066
[1m255/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 54ms/step - accuracy: 0.2396 - loss: 2.3066
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m563/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.2699 - loss: 2.2006
[1m565/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.2699 - loss: 2.2006[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m351/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2784 - loss: 2.2035[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 41ms/step - accuracy: 0.3020 - loss: 2.1255[32m [repeated 285x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 63ms/step - accuracy: 0.2597 - loss: 2.2660
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 63ms/step - accuracy: 0.2597 - loss: 2.2660[32m [repeated 209x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m281/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 53ms/step - accuracy: 0.2391 - loss: 2.3075
[1m282/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.2391 - loss: 2.3076[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 92/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 46ms/step - accuracy: 0.1986 - loss: 2.4131[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m291/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.2389 - loss: 2.3078
[1m292/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.2389 - loss: 2.3078
[1m293/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.2388 - loss: 2.3079
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 60ms/step - accuracy: 0.2869 - loss: 2.1486
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 60ms/step - accuracy: 0.2869 - loss: 2.1486[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m74s[0m 64ms/step - accuracy: 0.2151 - loss: 2.4114 - val_accuracy: 0.2914 - val_loss: 2.2280
[36m(train_cnn_ray_tune pid=2697817)[0m Epoch 5/27
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2136 - loss: 2.4758[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:05[0m 109ms/step - accuracy: 0.1875 - loss: 2.2371
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:33[0m 81ms/step - accuracy: 0.2188 - loss: 2.2288 
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 67ms/step - accuracy: 0.2292 - loss: 2.2432
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 68ms/step - accuracy: 0.2383 - loss: 2.2630
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 6/27
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.2406 - loss: 2.2862
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.2439 - loss: 2.2947
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.2487 - loss: 2.2971
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.2488 - loss: 2.3022
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 65ms/step - accuracy: 0.2489 - loss: 2.3050
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.2490 - loss: 2.3108
[1m  12/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.2495 - loss: 2.3135
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.2488 - loss: 2.3164
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.2489 - loss: 2.3187
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m30s[0m 44ms/step - accuracy: 0.1510 - loss: 2.7547
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m30s[0m 44ms/step - accuracy: 0.1510 - loss: 2.7547
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m30s[0m 44ms/step - accuracy: 0.1510 - loss: 2.7547[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.2484 - loss: 2.3224
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.2473 - loss: 2.3275
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.2460 - loss: 2.3327
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.2444 - loss: 2.3386
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.2699 - loss: 2.2006 - val_accuracy: 0.3040 - val_loss: 2.2427
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.2422 - loss: 2.3499
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2421 - loss: 2.3520
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 49ms/step - accuracy: 0.2137 - loss: 2.4750
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 49ms/step - accuracy: 0.2137 - loss: 2.4750
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 49ms/step - accuracy: 0.2137 - loss: 2.4750
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 65ms/step - accuracy: 0.2394 - loss: 2.3577
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 65ms/step - accuracy: 0.2391 - loss: 2.3577
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  34/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.2381 - loss: 2.3575
[1m  35/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.2379 - loss: 2.3578
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  45/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2393 - loss: 2.3540
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2395 - loss: 2.3536
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  47/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2397 - loss: 2.3531
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2399 - loss: 2.3525
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2401 - loss: 2.3519
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.2402 - loss: 2.3514
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 34ms/step - accuracy: 0.2773 - loss: 2.2013
[1m480/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 34ms/step - accuracy: 0.2773 - loss: 2.2013[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.2406 - loss: 2.3503
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.2408 - loss: 2.3497
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.2410 - loss: 2.3490
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 64ms/step - accuracy: 0.2412 - loss: 2.3482
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m365/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.2680 - loss: 2.2272[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 64ms/step - accuracy: 0.2416 - loss: 2.3461
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 64ms/step - accuracy: 0.2416 - loss: 2.3456
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m10s[0m 50ms/step - accuracy: 0.2243 - loss: 2.3760[32m [repeated 237x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.1759 - loss: 2.6122
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 36ms/step - accuracy: 0.1759 - loss: 2.6122[32m [repeated 197x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:20[0m 139ms/step - accuracy: 0.1562 - loss: 2.8495
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 72ms/step - accuracy: 0.1719 - loss: 2.8145  
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  62/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 64ms/step - accuracy: 0.2418 - loss: 2.3440
[1m  63/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.2418 - loss: 2.3436
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  64/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 64ms/step - accuracy: 0.2418 - loss: 2.3433
[1m  65/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.2418 - loss: 2.3430
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  66/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.2419 - loss: 2.3427
[1m  67/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.2419 - loss: 2.3425
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m200/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 46ms/step - accuracy: 0.2004 - loss: 2.4194
[1m202/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 46ms/step - accuracy: 0.2004 - loss: 2.4195[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m374/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 54ms/step - accuracy: 0.2380 - loss: 2.3099[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  70/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2419 - loss: 2.3417
[1m  71/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2418 - loss: 2.3415
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  72/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.2418 - loss: 2.3413
[1m  73/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2418 - loss: 2.3412
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  74/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 64ms/step - accuracy: 0.2417 - loss: 2.3410
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2417 - loss: 2.3409
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.2244 - loss: 2.3758
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.2244 - loss: 2.3758[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2416 - loss: 2.3407
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2416 - loss: 2.3405
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m55s[0m 47ms/step - accuracy: 0.2021 - loss: 2.5656 - val_accuracy: 0.2773 - val_loss: 2.2487
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2415 - loss: 2.3403
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2415 - loss: 2.3402
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 62ms/step - accuracy: 0.2596 - loss: 2.2648[32m [repeated 120x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 94ms/step - accuracy: 0.2188 - loss: 2.1167[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 63ms/step - accuracy: 0.2414 - loss: 2.3399
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 63ms/step - accuracy: 0.2413 - loss: 2.3397
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 63ms/step - accuracy: 0.2413 - loss: 2.3397
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 63ms/step - accuracy: 0.2412 - loss: 2.3397
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 10/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 62ms/step - accuracy: 0.2410 - loss: 2.3393[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  94/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 61ms/step - accuracy: 0.2407 - loss: 2.3384
[1m  95/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 61ms/step - accuracy: 0.2406 - loss: 2.3383
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m27s[0m 49ms/step - accuracy: 0.1274 - loss: 2.9392
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m26s[0m 49ms/step - accuracy: 0.1274 - loss: 2.9392
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m26s[0m 49ms/step - accuracy: 0.1274 - loss: 2.9392[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 100/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2402 - loss: 2.3380
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2401 - loss: 2.3379
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2400 - loss: 2.3378
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2399 - loss: 2.3377
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 60ms/step - accuracy: 0.1891 - loss: 2.6792 - val_accuracy: 0.2521 - val_loss: 2.3508
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2399 - loss: 2.3376
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2399 - loss: 2.3375
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m415/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 54ms/step - accuracy: 0.2378 - loss: 2.3105
[1m416/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 54ms/step - accuracy: 0.2378 - loss: 2.3105
[1m417/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 54ms/step - accuracy: 0.2378 - loss: 2.3105
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 49ms/step - accuracy: 0.2245 - loss: 2.3755
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 49ms/step - accuracy: 0.2245 - loss: 2.3755
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 49ms/step - accuracy: 0.2245 - loss: 2.3755
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2398 - loss: 2.3374
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 61ms/step - accuracy: 0.2398 - loss: 2.3374
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 49ms/step - accuracy: 0.2245 - loss: 2.3754
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 49ms/step - accuracy: 0.2245 - loss: 2.3754
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m7s[0m 49ms/step - accuracy: 0.2245 - loss: 2.3754
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.2397 - loss: 2.3372
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 60ms/step - accuracy: 0.2397 - loss: 2.3371
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 117/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.2395 - loss: 2.3367
[1m 119/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.2395 - loss: 2.3366
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 120/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.2395 - loss: 2.3365
[1m 121/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.2395 - loss: 2.3365
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 123/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.2394 - loss: 2.3364
[1m 124/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.2394 - loss: 2.3363
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.2395 - loss: 2.3357
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.2394 - loss: 2.3357
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.2394 - loss: 2.3356
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2394 - loss: 2.3356
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2394 - loss: 2.3355
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2394 - loss: 2.3355
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m445/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 54ms/step - accuracy: 0.2377 - loss: 2.3107
[1m446/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 54ms/step - accuracy: 0.2377 - loss: 2.3107[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 37ms/step - accuracy: 0.2769 - loss: 2.1996 - val_accuracy: 0.3339 - val_loss: 2.1352
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m494/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 43ms/step - accuracy: 0.2676 - loss: 2.2263[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m40s[0m 42ms/step - accuracy: 0.2033 - loss: 2.5237[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m21s[0m 48ms/step - accuracy: 0.1273 - loss: 2.9386
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m21s[0m 48ms/step - accuracy: 0.1273 - loss: 2.9385[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 26/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2425 - loss: 2.2904
[1m 28/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 35ms/step - accuracy: 0.2445 - loss: 2.2839[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m323/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 44ms/step - accuracy: 0.2022 - loss: 2.4214[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 49ms/step - accuracy: 0.2248 - loss: 2.3744
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 49ms/step - accuracy: 0.2248 - loss: 2.3744[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.3008 - loss: 2.1265[32m [repeated 136x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:25[0m 149ms/step - accuracy: 0.0938 - loss: 2.6137
[36m(train_cnn_ray_tune pid=2697881)[0m Epoch 15/20
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 59ms/step - accuracy: 0.2394 - loss: 2.3354 [32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m353/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.2026 - loss: 2.4215 
[1m355/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.2026 - loss: 2.4215
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m63s[0m 54ms/step - accuracy: 0.2169 - loss: 2.3922 - val_accuracy: 0.2672 - val_loss: 2.2621
[36m(train_cnn_ray_tune pid=2697885)[0m Epoch 6/25
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:26[0m 127ms/step - accuracy: 0.0625 - loss: 3.1568
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1250 - loss: 2.9632 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.1528 - loss: 2.8604
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.2317 - loss: 2.3254
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.2316 - loss: 2.3254
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.2316 - loss: 2.3254
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.1818 - loss: 2.6661
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1885 - loss: 2.6057
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1935 - loss: 2.5629 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1940 - loss: 2.5479
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 62ms/step - accuracy: 0.2597 - loss: 2.2639
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 62ms/step - accuracy: 0.2597 - loss: 2.2638
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 62ms/step - accuracy: 0.2597 - loss: 2.2638
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m522/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 53ms/step - accuracy: 0.2377 - loss: 2.3103
[1m523/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 53ms/step - accuracy: 0.2377 - loss: 2.3103
[1m524/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 53ms/step - accuracy: 0.2377 - loss: 2.3103
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m407/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 44ms/step - accuracy: 0.2032 - loss: 2.4213
[1m409/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 44ms/step - accuracy: 0.2032 - loss: 2.4213[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3260
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3260
[1m 644/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3261
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2305 - loss: 2.3262
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2305 - loss: 2.3262
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2304 - loss: 2.3262
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m563/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 53ms/step - accuracy: 0.2377 - loss: 2.3103[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:48[0m 94ms/step - accuracy: 0.3125 - loss: 2.2611
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 33ms/step - accuracy: 0.2639 - loss: 2.3438 
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  63/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 45ms/step - accuracy: 0.2159 - loss: 2.4064[32m [repeated 172x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2304 - loss: 2.3262
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2304 - loss: 2.3263[32m [repeated 132x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1763 - loss: 2.6114
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1763 - loss: 2.6114
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.1763 - loss: 2.6114
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m204/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 51ms/step - accuracy: 0.1913 - loss: 2.6523
[1m206/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 51ms/step - accuracy: 0.1914 - loss: 2.6519[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m191/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m12s[0m 31ms/step - accuracy: 0.2740 - loss: 2.1888[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 48ms/step - accuracy: 0.2673 - loss: 2.2261 - val_accuracy: 0.3028 - val_loss: 2.2302
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.1919 - loss: 2.4598
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.1919 - loss: 2.4598[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2066 - loss: 2.2855  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2190 - loss: 2.3062
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 32ms/step - accuracy: 0.1919 - loss: 2.4598[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  65/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 54ms/step - accuracy: 0.2997 - loss: 2.1006 [32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.1549 - loss: 2.7417 
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.1549 - loss: 2.7416
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m63s[0m 54ms/step - accuracy: 0.2140 - loss: 2.4719 - val_accuracy: 0.2682 - val_loss: 2.1953[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 12/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 106ms/step - accuracy: 0.2188 - loss: 2.2451[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m252/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2749 - loss: 2.1866 
[1m254/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2749 - loss: 2.1865
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.2812 - loss: 2.0125 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.2847 - loss: 2.0527
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 80ms/step - accuracy: 0.3594 - loss: 1.9396 
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  61/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2999 - loss: 2.1005
[1m  63/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.2998 - loss: 2.1005[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 51ms/step - accuracy: 0.3052 - loss: 1.9850 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 45ms/step - accuracy: 0.2950 - loss: 1.9979
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m533/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 43ms/step - accuracy: 0.2041 - loss: 2.4212
[1m535/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 43ms/step - accuracy: 0.2041 - loss: 2.4212[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m551/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.2042 - loss: 2.4212[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 105ms/step - accuracy: 0.1875 - loss: 2.4264
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 53ms/step - accuracy: 0.1797 - loss: 2.4505  
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 144/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 54ms/step - accuracy: 0.3021 - loss: 2.0967[32m [repeated 242x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m  68/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 38ms/step - accuracy: 0.3038 - loss: 2.0627
[1m  70/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 38ms/step - accuracy: 0.3037 - loss: 2.0639[32m [repeated 180x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:13[0m 116ms/step - accuracy: 0.2500 - loss: 2.3563
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 35ms/step - accuracy: 0.2083 - loss: 2.3911  
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m313/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 49ms/step - accuracy: 0.1937 - loss: 2.6382
[1m315/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 49ms/step - accuracy: 0.1938 - loss: 2.6380[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 40/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 42ms/step - accuracy: 0.2267 - loss: 2.3085[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.4844 - loss: 1.8346  
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.4410 - loss: 1.8619
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 58ms/step - accuracy: 0.2376 - loss: 2.3104 - val_accuracy: 0.2883 - val_loss: 2.2275
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 47ms/step - accuracy: 0.1272 - loss: 2.9376
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 47ms/step - accuracy: 0.1272 - loss: 2.9376[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m  37/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.1914 - loss: 2.4921
[1m  39/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 31ms/step - accuracy: 0.1911 - loss: 2.4921
[1m  41/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 31ms/step - accuracy: 0.1910 - loss: 2.4923
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 47ms/step - accuracy: 0.1273 - loss: 2.9376[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 66ms/step - accuracy: 0.3368 - loss: 1.9566
Trial status: 20 RUNNING
Current time: 2025-11-07 12:45:52. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.1272 - loss: 2.9377 
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.1272 - loss: 2.9377
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m80s[0m 69ms/step - accuracy: 0.2598 - loss: 2.2633 - val_accuracy: 0.3264 - val_loss: 2.1399[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m Epoch 5/23[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:20[0m 173ms/step - accuracy: 0.1250 - loss: 2.4572[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:24[0m 73ms/step - accuracy: 0.1910 - loss: 2.3735
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 68ms/step - accuracy: 0.2436 - loss: 2.2858
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 79ms/step - accuracy: 0.1719 - loss: 2.4004 
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 67ms/step - accuracy: 0.2174 - loss: 2.3326
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 65ms/step - accuracy: 0.2340 - loss: 2.3049[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 68ms/step - accuracy: 0.2483 - loss: 2.2747
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.2598 - loss: 2.2339
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2634 - loss: 2.2232
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2650 - loss: 2.2192
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2659 - loss: 2.2177
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2673 - loss: 2.2158
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2703 - loss: 2.2111
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2718 - loss: 2.2081
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2731 - loss: 2.2053
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.2741 - loss: 2.2031
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  33/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.2792 - loss: 2.1926
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 49ms/step - accuracy: 0.2044 - loss: 2.4211 - val_accuracy: 0.2770 - val_loss: 2.2648
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  35/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.2795 - loss: 2.1925
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  36/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2795 - loss: 2.1926
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  37/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.2794 - loss: 2.1930
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  38/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2792 - loss: 2.1937
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m476/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 31ms/step - accuracy: 0.2772 - loss: 2.1817
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 31ms/step - accuracy: 0.2772 - loss: 2.1817[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  39/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2791 - loss: 2.1945
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  40/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 61ms/step - accuracy: 0.2789 - loss: 2.1954
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m402/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.1940 - loss: 2.6333[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 52ms/step - accuracy: 0.2868 - loss: 2.1702[32m [repeated 249x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m41s[0m 44ms/step - accuracy: 0.2272 - loss: 2.3991
[1m 230/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m40s[0m 44ms/step - accuracy: 0.2271 - loss: 2.3993[32m [repeated 191x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.2775 - loss: 2.2054
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:39[0m 86ms/step - accuracy: 0.0000e+00 - loss: 2.7285
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 33ms/step - accuracy: 0.0833 - loss: 2.5934     
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.2775 - loss: 2.2073
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.2776 - loss: 2.2090
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 22/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 46ms/step - accuracy: 0.2042 - loss: 2.4391
[1m 23/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 46ms/step - accuracy: 0.2047 - loss: 2.4372[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 27/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 46ms/step - accuracy: 0.2060 - loss: 2.4333[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.2776 - loss: 2.2095
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 47ms/step - accuracy: 0.1273 - loss: 2.9375
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 47ms/step - accuracy: 0.1273 - loss: 2.9375[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  67/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.2779 - loss: 2.2132
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  68/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.2779 - loss: 2.2135
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  69/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2778 - loss: 2.2137
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 61ms/step - accuracy: 0.3438 - loss: 2.0753  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.3066 - loss: 2.1406
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 47ms/step - accuracy: 0.1273 - loss: 2.9375[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  72/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2778 - loss: 2.2144
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  73/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.2778 - loss: 2.2146
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  74/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.2777 - loss: 2.2149
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.2777 - loss: 2.2151
[36m(train_cnn_ray_tune pid=2697828)[0m Epoch 14/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 124ms/step - accuracy: 0.3438 - loss: 2.0706[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 35ms/step - accuracy: 0.1675 - loss: 2.5669
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 36ms/step - accuracy: 0.1675 - loss: 2.5669
[1m 201/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m33s[0m 36ms/step - accuracy: 0.1675 - loss: 2.5669
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2770 - loss: 2.2184
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2770 - loss: 2.2180
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2770 - loss: 2.2182[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2770 - loss: 2.2187
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2770 - loss: 2.2188
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  89/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 64ms/step - accuracy: 0.2769 - loss: 2.2190
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  96/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2770 - loss: 2.2195
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  97/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2769 - loss: 2.2196
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  98/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2769 - loss: 2.2197
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  99/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2769 - loss: 2.2198
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 100/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2769 - loss: 2.2198
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 65ms/step - accuracy: 0.2769 - loss: 2.2199
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2768 - loss: 2.2201
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.2743 - loss: 2.1792 - val_accuracy: 0.3069 - val_loss: 2.2124
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2768 - loss: 2.2201
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2768 - loss: 2.2201
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m485/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 50ms/step - accuracy: 0.1938 - loss: 2.6319
[1m487/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 50ms/step - accuracy: 0.1938 - loss: 2.6318[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 64ms/step - accuracy: 0.2767 - loss: 2.2202
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2767 - loss: 2.2202
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 117/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2767 - loss: 2.2202
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 122/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2766 - loss: 2.2201
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m496/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 50ms/step - accuracy: 0.1938 - loss: 2.6316[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 124/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 64ms/step - accuracy: 0.2766 - loss: 2.2202
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 125/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 64ms/step - accuracy: 0.2766 - loss: 2.2202
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m35s[0m 56ms/step - accuracy: 0.2330 - loss: 2.3501[32m [repeated 241x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 310/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m48s[0m 57ms/step - accuracy: 0.3007 - loss: 2.0975
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m48s[0m 57ms/step - accuracy: 0.3007 - loss: 2.0975[32m [repeated 189x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 36ms/step - accuracy: 0.2771 - loss: 2.1804 - val_accuracy: 0.3407 - val_loss: 2.1188
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m138/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 45ms/step - accuracy: 0.2062 - loss: 2.4174
[1m139/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 45ms/step - accuracy: 0.2062 - loss: 2.4173[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m217/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 54ms/step - accuracy: 0.2351 - loss: 2.3001[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m349/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.2671 - loss: 2.2255
[1m350/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.2671 - loss: 2.2254
[1m352/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.2672 - loss: 2.2254
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m218/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 55ms/step - accuracy: 0.2351 - loss: 2.3001
[1m219/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 55ms/step - accuracy: 0.2351 - loss: 2.3000
[1m220/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 55ms/step - accuracy: 0.2351 - loss: 2.3000
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 64ms/step - accuracy: 0.2762 - loss: 2.2198
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.2178 - loss: 2.3934
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.2178 - loss: 2.3934[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 149/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.2762 - loss: 2.2195
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 150/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 64ms/step - accuracy: 0.2762 - loss: 2.2195
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 151/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 63ms/step - accuracy: 0.2762 - loss: 2.2194
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.2178 - loss: 2.3934[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 152/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 64ms/step - accuracy: 0.2762 - loss: 2.2194
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 153/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 64ms/step - accuracy: 0.2761 - loss: 2.2194
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 64ms/step - accuracy: 0.2761 - loss: 2.2194
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 64ms/step - accuracy: 0.2761 - loss: 2.2193
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 64ms/step - accuracy: 0.2761 - loss: 2.2193
[36m(train_cnn_ray_tune pid=2697881)[0m Epoch 16/20
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 90ms/step - accuracy: 0.3438 - loss: 2.0594
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m37s[0m 47ms/step - accuracy: 0.2247 - loss: 2.4021
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m37s[0m 47ms/step - accuracy: 0.2247 - loss: 2.4021
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m37s[0m 47ms/step - accuracy: 0.2247 - loss: 2.4021
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 64ms/step - accuracy: 0.2760 - loss: 2.2190
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 63ms/step - accuracy: 0.2760 - loss: 2.2189[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m54s[0m 47ms/step - accuracy: 0.1562 - loss: 2.7365 - val_accuracy: 0.2547 - val_loss: 2.3186
[36m(train_cnn_ray_tune pid=2697856)[0m Epoch 7/29
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:13[0m 116ms/step - accuracy: 0.2500 - loss: 2.6585
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1667 - loss: 2.9169 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.1562 - loss: 2.9116
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.1458 - loss: 2.9032 
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m435/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.2680 - loss: 2.2216
[1m436/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.2680 - loss: 2.2216[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 36ms/step - accuracy: 0.1979 - loss: 2.5119  
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m447/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.2681 - loss: 2.2212[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m33s[0m 47ms/step - accuracy: 0.2247 - loss: 2.4028[32m [repeated 243x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m26s[0m 36ms/step - accuracy: 0.1709 - loss: 2.5763
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m26s[0m 36ms/step - accuracy: 0.1709 - loss: 2.5763[32m [repeated 202x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m311/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 53ms/step - accuracy: 0.2364 - loss: 2.2961
[1m312/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 53ms/step - accuracy: 0.2365 - loss: 2.2961
[1m313/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.2365 - loss: 2.2961
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 63ms/step - accuracy: 0.2758 - loss: 2.2182 
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m59s[0m 63ms/step - accuracy: 0.2758 - loss: 2.2182
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m318/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.2365 - loss: 2.2959
[1m320/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 53ms/step - accuracy: 0.2366 - loss: 2.2958[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m157/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.2864 - loss: 2.1555[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.2179 - loss: 2.3933
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 43ms/step - accuracy: 0.2179 - loss: 2.3933[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 43ms/step - accuracy: 0.2179 - loss: 2.3932[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 56ms/step - accuracy: 0.1938 - loss: 2.6304 - val_accuracy: 0.2585 - val_loss: 2.3345
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m28s[0m 57ms/step - accuracy: 0.2331 - loss: 2.3505
[1m 644/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m28s[0m 57ms/step - accuracy: 0.2331 - loss: 2.3505
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m28s[0m 57ms/step - accuracy: 0.2331 - loss: 2.3505
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 106ms/step - accuracy: 0.1875 - loss: 2.6885
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 65ms/step - accuracy: 0.1797 - loss: 2.7103  
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 63ms/step - accuracy: 0.2758 - loss: 2.2182
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 63ms/step - accuracy: 0.2758 - loss: 2.2182[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m61s[0m 53ms/step - accuracy: 0.1274 - loss: 2.9372 - val_accuracy: 0.1973 - val_loss: 2.5248[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 11/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:03[0m 107ms/step - accuracy: 0.2500 - loss: 2.9073[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1170 - loss: 2.9939 [32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m540/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 43ms/step - accuracy: 0.2684 - loss: 2.2191
[1m542/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 43ms/step - accuracy: 0.2684 - loss: 2.2191[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:16[0m 66ms/step - accuracy: 0.1597 - loss: 3.1139 
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m367/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 37ms/step - accuracy: 0.2863 - loss: 2.1491[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m26s[0m 56ms/step - accuracy: 0.2330 - loss: 2.3507[32m [repeated 341x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m54s[0m 63ms/step - accuracy: 0.2749 - loss: 2.2192
[1m 288/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m54s[0m 63ms/step - accuracy: 0.2749 - loss: 2.2193[32m [repeated 250x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m352/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 46ms/step - accuracy: 0.2097 - loss: 2.4093
[1m354/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 46ms/step - accuracy: 0.2097 - loss: 2.4092[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 65/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 49ms/step - accuracy: 0.2067 - loss: 2.5818[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m361/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.2097 - loss: 2.4091 
[1m363/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.2097 - loss: 2.4091
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 40ms/step - accuracy: 0.2074 - loss: 2.5248
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 40ms/step - accuracy: 0.2074 - loss: 2.5248[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 40ms/step - accuracy: 0.2074 - loss: 2.5247[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 47ms/step - accuracy: 0.1180 - loss: 2.9031
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 47ms/step - accuracy: 0.1181 - loss: 2.9028
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 47ms/step - accuracy: 0.1182 - loss: 2.9024
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m60s[0m 52ms/step - accuracy: 0.2179 - loss: 2.3932 - val_accuracy: 0.2593 - val_loss: 2.2214
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 7/27
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m36s[0m 58ms/step - accuracy: 0.2994 - loss: 2.0994
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m36s[0m 58ms/step - accuracy: 0.2994 - loss: 2.0995
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m36s[0m 58ms/step - accuracy: 0.2994 - loss: 2.0995
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 49ms/step - accuracy: 0.2685 - loss: 2.2184 - val_accuracy: 0.3018 - val_loss: 2.2076
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 13/27
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 102ms/step - accuracy: 0.3438 - loss: 2.1897
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m486/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 53ms/step - accuracy: 0.2376 - loss: 2.2918
[1m487/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 53ms/step - accuracy: 0.2376 - loss: 2.2917[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m439/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2795 - loss: 2.1619[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m35s[0m 42ms/step - accuracy: 0.1605 - loss: 2.7235[32m [repeated 334x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m48s[0m 62ms/step - accuracy: 0.2738 - loss: 2.2214
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m48s[0m 62ms/step - accuracy: 0.2738 - loss: 2.2215[32m [repeated 253x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 29/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 41ms/step - accuracy: 0.2464 - loss: 2.2774
[1m 30/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 41ms/step - accuracy: 0.2470 - loss: 2.2750[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 31/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 42ms/step - accuracy: 0.2475 - loss: 2.2728[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 40ms/step - accuracy: 0.2078 - loss: 2.5236
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 40ms/step - accuracy: 0.2078 - loss: 2.5236[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.2079 - loss: 2.5234[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m20s[0m 56ms/step - accuracy: 0.2328 - loss: 2.3506
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m20s[0m 56ms/step - accuracy: 0.2328 - loss: 2.3506
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m20s[0m 56ms/step - accuracy: 0.2328 - loss: 2.3506[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m201/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 52ms/step - accuracy: 0.1968 - loss: 2.6007
[1m202/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 52ms/step - accuracy: 0.1967 - loss: 2.6008
[1m203/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m19s[0m 52ms/step - accuracy: 0.1967 - loss: 2.6008
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m556/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 53ms/step - accuracy: 0.2380 - loss: 2.2903
[1m557/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 53ms/step - accuracy: 0.2380 - loss: 2.2903
[1m558/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 53ms/step - accuracy: 0.2380 - loss: 2.2903
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m230/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 51ms/step - accuracy: 0.1958 - loss: 2.6021
[1m231/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 51ms/step - accuracy: 0.1958 - loss: 2.6021
[1m232/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 51ms/step - accuracy: 0.1957 - loss: 2.6021
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m574/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.2785 - loss: 2.1637
[1m576/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.2785 - loss: 2.1637[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m572/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 45ms/step - accuracy: 0.2105 - loss: 2.4069[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m18s[0m 46ms/step - accuracy: 0.2257 - loss: 2.4033[32m [repeated 304x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m42s[0m 61ms/step - accuracy: 0.2733 - loss: 2.2222
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m42s[0m 61ms/step - accuracy: 0.2733 - loss: 2.2222[32m [repeated 248x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 42ms/step - accuracy: 0.2856 - loss: 2.1518 - val_accuracy: 0.2964 - val_loss: 2.2006
[36m(train_cnn_ray_tune pid=2697828)[0m Epoch 15/27
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m256/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 51ms/step - accuracy: 0.1954 - loss: 2.6027
[1m258/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 51ms/step - accuracy: 0.1953 - loss: 2.6027[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m261/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 51ms/step - accuracy: 0.1953 - loss: 2.6027[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 89ms/step - accuracy: 0.2812 - loss: 2.4848
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.3038 - loss: 2.2419
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 873/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.1736 - loss: 2.5803 
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.1736 - loss: 2.5803
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.1736 - loss: 2.5803
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.1736 - loss: 2.5803[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.1737 - loss: 2.5803[32m [repeated 32x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-07 12:46:22. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 119ms/step - accuracy: 0.0938 - loss: 2.7954
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 32ms/step - accuracy: 0.2207 - loss: 2.3245
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 32ms/step - accuracy: 0.2207 - loss: 2.3244
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 32ms/step - accuracy: 0.2208 - loss: 2.3244[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m52s[0m 45ms/step - accuracy: 0.2080 - loss: 2.5232 - val_accuracy: 0.2815 - val_loss: 2.2243
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.1739 - loss: 2.5803
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.1739 - loss: 2.5803
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.1739 - loss: 2.5803
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m574/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 45ms/step - accuracy: 0.2105 - loss: 2.4069
[1m575/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 45ms/step - accuracy: 0.2105 - loss: 2.4069
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 45ms/step - accuracy: 0.2105 - loss: 2.4069
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m36s[0m 60ms/step - accuracy: 0.2731 - loss: 2.2211[32m [repeated 268x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m34s[0m 45ms/step - accuracy: 0.1299 - loss: 2.8798
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m34s[0m 45ms/step - accuracy: 0.1299 - loss: 2.8797[32m [repeated 213x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 50ms/step - accuracy: 0.2105 - loss: 2.4069 - val_accuracy: 0.2829 - val_loss: 2.2490[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 7/27[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m269/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 42ms/step - accuracy: 0.2621 - loss: 2.2197
[1m271/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 42ms/step - accuracy: 0.2622 - loss: 2.2195[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 60/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 46ms/step - accuracy: 0.2125 - loss: 2.3943[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:05[0m 109ms/step - accuracy: 0.1875 - loss: 2.4814
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.1562 - loss: 2.5617  
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m378/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6016 
[1m380/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6016
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 35ms/step - accuracy: 0.1743 - loss: 2.5801
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 35ms/step - accuracy: 0.1743 - loss: 2.5801[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m381/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6016
[1m383/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6016
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m385/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6016
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m386/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6016
[1m387/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6016
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m389/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6016
[1m390/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6015
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 56ms/step - accuracy: 0.2324 - loss: 2.3502[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m391/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6015
[1m392/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6015
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m394/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6015
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m396/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6015
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m397/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6015
[1m398/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6015
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m400/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6015
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m402/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6015
[1m403/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6015
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m404/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6015
[1m406/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6014
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 98ms/step - accuracy: 0.2188 - loss: 2.3977
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m408/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.1950 - loss: 2.6014
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m410/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.1951 - loss: 2.6014
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m412/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 49ms/step - accuracy: 0.1951 - loss: 2.6014
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m414/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 49ms/step - accuracy: 0.1951 - loss: 2.6013
[1m416/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 49ms/step - accuracy: 0.1951 - loss: 2.6013
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m34s[0m 45ms/step - accuracy: 0.1297 - loss: 2.8801
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m34s[0m 45ms/step - accuracy: 0.1297 - loss: 2.8801
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m34s[0m 45ms/step - accuracy: 0.1298 - loss: 2.8800
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m417/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1951 - loss: 2.6013
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m419/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1951 - loss: 2.6012
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m421/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1951 - loss: 2.6012
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m423/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1951 - loss: 2.6012
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m425/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1951 - loss: 2.6011
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m427/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1951 - loss: 2.6011
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m429/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1952 - loss: 2.6010
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m431/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1952 - loss: 2.6010
[1m432/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1952 - loss: 2.6010
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m433/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1952 - loss: 2.6009
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m434/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1952 - loss: 2.6009
[1m435/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.1952 - loss: 2.6009
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m439/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 49ms/step - accuracy: 0.1952 - loss: 2.6008
[1m440/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 49ms/step - accuracy: 0.1952 - loss: 2.6008
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m31s[0m 60ms/step - accuracy: 0.2732 - loss: 2.2198[32m [repeated 221x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m31s[0m 60ms/step - accuracy: 0.2732 - loss: 2.2198
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m31s[0m 60ms/step - accuracy: 0.2732 - loss: 2.2198[32m [repeated 168x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 35ms/step - accuracy: 0.1992 - loss: 2.4529 - val_accuracy: 0.2676 - val_loss: 2.2391
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:54[0m 99ms/step - accuracy: 0.5000 - loss: 1.9641
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.3299 - loss: 2.2539 
[36m(train_cnn_ray_tune pid=2697874)[0m Epoch 10/18
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m158/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 51ms/step - accuracy: 0.2514 - loss: 2.2797
[1m160/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 51ms/step - accuracy: 0.2515 - loss: 2.2794[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m156/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 51ms/step - accuracy: 0.2513 - loss: 2.2799[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 46ms/step - accuracy: 0.2233 - loss: 2.3481
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 46ms/step - accuracy: 0.2233 - loss: 2.3481[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m489/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 49ms/step - accuracy: 0.1956 - loss: 2.5998
[1m490/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 49ms/step - accuracy: 0.1956 - loss: 2.5998[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m492/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 49ms/step - accuracy: 0.1956 - loss: 2.5998[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m15s[0m 49ms/step - accuracy: 0.2488 - loss: 2.2928
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m15s[0m 49ms/step - accuracy: 0.2488 - loss: 2.2928
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m15s[0m 49ms/step - accuracy: 0.2488 - loss: 2.2929
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2250 - loss: 2.3163[32m [repeated 137x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 56ms/step - accuracy: 0.2323 - loss: 2.3496
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 56ms/step - accuracy: 0.2323 - loss: 2.3496
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 56ms/step - accuracy: 0.2323 - loss: 2.3496
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:03:39[0m 22s/step - accuracy: 0.2500 - loss: 2.3316
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.2344 - loss: 2.3935   
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 46ms/step - accuracy: 0.2331 - loss: 2.3643
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 9/26
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 40ms/step - accuracy: 0.1658 - loss: 2.6965[32m [repeated 175x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 60ms/step - accuracy: 0.2731 - loss: 2.2190
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m25s[0m 60ms/step - accuracy: 0.2731 - loss: 2.2190[32m [repeated 157x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m45s[0m 39ms/step - accuracy: 0.1749 - loss: 2.5797 - val_accuracy: 0.2237 - val_loss: 2.2959
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.3125 - loss: 2.6237  
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.2889 - loss: 2.5455
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.2737 - loss: 2.5386 
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 45ms/step - accuracy: 0.2677 - loss: 2.5278
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m252/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 52ms/step - accuracy: 0.2525 - loss: 2.2716
[1m253/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 52ms/step - accuracy: 0.2525 - loss: 2.2716[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m255/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 52ms/step - accuracy: 0.2525 - loss: 2.2714[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 46ms/step - accuracy: 0.2260 - loss: 2.4029
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 46ms/step - accuracy: 0.2260 - loss: 2.4029[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m437/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 36ms/step - accuracy: 0.2844 - loss: 2.1522
[1m439/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 36ms/step - accuracy: 0.2844 - loss: 2.1522[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m532/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 42ms/step - accuracy: 0.2674 - loss: 2.2073[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m15s[0m 57ms/step - accuracy: 0.2981 - loss: 2.1019
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m15s[0m 57ms/step - accuracy: 0.2981 - loss: 2.1019
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m15s[0m 57ms/step - accuracy: 0.2981 - loss: 2.1019
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.2483 - loss: 2.2947 
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.2483 - loss: 2.2947
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m50s[0m 43ms/step - accuracy: 0.3082 - loss: 2.0933 - val_accuracy: 0.3349 - val_loss: 2.0578
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 31ms/step - accuracy: 0.2260 - loss: 2.3145[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 55ms/step - accuracy: 0.1959 - loss: 2.5991 - val_accuracy: 0.2644 - val_loss: 2.3197
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 112ms/step - accuracy: 0.2812 - loss: 2.2180[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 12/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m19s[0m 59ms/step - accuracy: 0.2729 - loss: 2.2181[32m [repeated 219x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 29ms/step - accuracy: 0.1989 - loss: 2.4330
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 29ms/step - accuracy: 0.1989 - loss: 2.4329[32m [repeated 182x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.4167 - loss: 1.7824  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m357/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 51ms/step - accuracy: 0.2526 - loss: 2.2679
[1m358/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 51ms/step - accuracy: 0.2526 - loss: 2.2679
[1m359/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 51ms/step - accuracy: 0.2526 - loss: 2.2679
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 38/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 44ms/step - accuracy: 0.2038 - loss: 2.5846
[1m 40/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 43ms/step - accuracy: 0.2043 - loss: 2.5843[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m361/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 51ms/step - accuracy: 0.2526 - loss: 2.2678[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 59ms/step - accuracy: 0.2344 - loss: 2.1536 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2604 - loss: 2.1404
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2899 - loss: 2.2480  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.2986 - loss: 2.2091
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.2650 - loss: 2.1438 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 47ms/step - accuracy: 0.2652 - loss: 2.1548
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 40ms/step - accuracy: 0.1659 - loss: 2.6946
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 40ms/step - accuracy: 0.1659 - loss: 2.6946[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m440/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.2109 - loss: 2.3956
[1m442/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.2109 - loss: 2.3956[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 44ms/step - accuracy: 0.2361 - loss: 2.2555   
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m444/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 42ms/step - accuracy: 0.2109 - loss: 2.3956[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m379/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.2527 - loss: 2.2675 
[1m380/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 50ms/step - accuracy: 0.2527 - loss: 2.2675
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 57ms/step - accuracy: 0.2981 - loss: 2.1016 
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 57ms/step - accuracy: 0.2981 - loss: 2.1016
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m59s[0m 51ms/step - accuracy: 0.2235 - loss: 2.3476 - val_accuracy: 0.2714 - val_loss: 2.2399
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 57ms/step - accuracy: 0.2981 - loss: 2.1014[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 40ms/step - accuracy: 0.1659 - loss: 2.6943
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 40ms/step - accuracy: 0.1659 - loss: 2.6943
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 40ms/step - accuracy: 0.1659 - loss: 2.6943
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m72s[0m 62ms/step - accuracy: 0.2323 - loss: 2.3495 - val_accuracy: 0.2835 - val_loss: 2.2192
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 45ms/step - accuracy: 0.1111 - loss: 2.3286  
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2526 - loss: 2.1241
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 45ms/step - accuracy: 0.2441 - loss: 2.1573 
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 46ms/step - accuracy: 0.2681 - loss: 2.2055 - val_accuracy: 0.2970 - val_loss: 2.2239
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 41ms/step - accuracy: 0.2842 - loss: 2.1518 - val_accuracy: 0.3194 - val_loss: 2.1858
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:38[0m 138ms/step - accuracy: 0.0625 - loss: 2.4049
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 35ms/step - accuracy: 0.1424 - loss: 2.3206  
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 131ms/step - accuracy: 0.1562 - loss: 2.1413[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 10/24[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 59ms/step - accuracy: 0.2729 - loss: 2.2172[32m [repeated 229x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 45ms/step - accuracy: 0.1359 - loss: 2.8738
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 45ms/step - accuracy: 0.1359 - loss: 2.8738[32m [repeated 177x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 84/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 46ms/step - accuracy: 0.2086 - loss: 2.5837
[1m 85/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 46ms/step - accuracy: 0.2086 - loss: 2.5838
[1m 86/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 46ms/step - accuracy: 0.2086 - loss: 2.5839
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m137/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 50ms/step - accuracy: 0.2088 - loss: 2.5804
[1m138/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 50ms/step - accuracy: 0.2088 - loss: 2.5803[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m136/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 50ms/step - accuracy: 0.2088 - loss: 2.5805[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m143/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 50ms/step - accuracy: 0.2088 - loss: 2.5800
[1m144/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 50ms/step - accuracy: 0.2088 - loss: 2.5799
[1m145/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 50ms/step - accuracy: 0.2088 - loss: 2.5798
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2656 - loss: 2.0886 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2535 - loss: 2.1095
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.1659 - loss: 2.6933
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.1659 - loss: 2.6932[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m554/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 42ms/step - accuracy: 0.2109 - loss: 2.3948
[1m555/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 42ms/step - accuracy: 0.2109 - loss: 2.3948[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.2000 - loss: 2.3068[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m560/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 42ms/step - accuracy: 0.2109 - loss: 2.3947[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 40ms/step - accuracy: 0.1659 - loss: 2.6931[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 34ms/step - accuracy: 0.2264 - loss: 2.3139 - val_accuracy: 0.2672 - val_loss: 2.2240[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  93/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2104 - loss: 2.3168
[1m  94/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 61ms/step - accuracy: 0.2106 - loss: 2.3169[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m10s[0m 59ms/step - accuracy: 0.2730 - loss: 2.2163
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m10s[0m 59ms/step - accuracy: 0.2730 - loss: 2.2163
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m10s[0m 59ms/step - accuracy: 0.2730 - loss: 2.2163
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m24s[0m 34ms/step - accuracy: 0.1944 - loss: 2.5657[32m [repeated 260x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m29s[0m 37ms/step - accuracy: 0.3176 - loss: 2.0599
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m29s[0m 37ms/step - accuracy: 0.3176 - loss: 2.0599[32m [repeated 202x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 48ms/step - accuracy: 0.2110 - loss: 2.3945 - val_accuracy: 0.2918 - val_loss: 2.2504
[36m(train_cnn_ray_tune pid=2697882)[0m Epoch 14/16
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m227/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 43ms/step - accuracy: 0.2871 - loss: 2.1689
[1m228/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m14s[0m 43ms/step - accuracy: 0.2871 - loss: 2.1690[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m235/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 51ms/step - accuracy: 0.2080 - loss: 2.5751[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 136ms/step - accuracy: 0.1562 - loss: 2.2505
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 46ms/step - accuracy: 0.1736 - loss: 2.2579  
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m242/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 51ms/step - accuracy: 0.2079 - loss: 2.5750
[1m243/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 51ms/step - accuracy: 0.2079 - loss: 2.5750
[1m244/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 51ms/step - accuracy: 0.2078 - loss: 2.5750
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 59ms/step - accuracy: 0.2730 - loss: 2.2161
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 59ms/step - accuracy: 0.2730 - loss: 2.2160[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m553/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 51ms/step - accuracy: 0.2520 - loss: 2.2666
[1m555/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 51ms/step - accuracy: 0.2520 - loss: 2.2666[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 144/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.2179 - loss: 2.3210[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m294/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2864 - loss: 2.1292[32m [repeated 34x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-07 12:46:52. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 59ms/step - accuracy: 0.2730 - loss: 2.2159[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 60ms/step - accuracy: 0.2191 - loss: 2.3214 
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 60ms/step - accuracy: 0.2192 - loss: 2.3214
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m63s[0m 54ms/step - accuracy: 0.2479 - loss: 2.2968 - val_accuracy: 0.3319 - val_loss: 2.1368
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 61ms/step - accuracy: 0.2188 - loss: 2.3212
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.2189 - loss: 2.3213[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:09[0m 112ms/step - accuracy: 0.1875 - loss: 2.4894
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 33ms/step - accuracy: 0.1910 - loss: 2.5517  
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2000 - loss: 2.4267 
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2000 - loss: 2.4267
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m25s[0m 40ms/step - accuracy: 0.2387 - loss: 2.3577[32m [repeated 199x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.1921 - loss: 2.5655
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 35ms/step - accuracy: 0.1921 - loss: 2.5655[32m [repeated 226x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 88ms/step - accuracy: 0.2578 - loss: 2.3359  
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 77ms/step - accuracy: 0.2587 - loss: 2.3408
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 57ms/step - accuracy: 0.2519 - loss: 2.2666 - val_accuracy: 0.2922 - val_loss: 2.2142
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 12/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m108/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m21s[0m 46ms/step - accuracy: 0.1990 - loss: 2.3731
[1m110/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m21s[0m 46ms/step - accuracy: 0.1993 - loss: 2.3731[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  7/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 63ms/step - accuracy: 0.2640 - loss: 2.3225[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:55[0m 100ms/step - accuracy: 0.3125 - loss: 2.2872
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.3438 - loss: 2.1912  
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 46ms/step - accuracy: 0.1372 - loss: 2.8722
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 46ms/step - accuracy: 0.1372 - loss: 2.8722[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m362/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.2847 - loss: 2.1733
[1m364/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 42ms/step - accuracy: 0.2847 - loss: 2.1733[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.2190 - loss: 2.3213[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m447/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 34ms/step - accuracy: 0.2833 - loss: 2.1369[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 46ms/step - accuracy: 0.1373 - loss: 2.8721[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 69ms/step - accuracy: 0.4688 - loss: 2.0022 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.4306 - loss: 2.0348
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m75s[0m 65ms/step - accuracy: 0.2983 - loss: 2.1010 - val_accuracy: 0.3296 - val_loss: 2.1217[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.3889 - loss: 1.9030
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.3872 - loss: 1.9046[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:36[0m 135ms/step - accuracy: 0.5000 - loss: 2.0009[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 46ms/step - accuracy: 0.1375 - loss: 2.8718
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 46ms/step - accuracy: 0.1375 - loss: 2.8717
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 46ms/step - accuracy: 0.1375 - loss: 2.8717
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2203 - loss: 2.4614 
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2203 - loss: 2.4614
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m21s[0m 41ms/step - accuracy: 0.2383 - loss: 2.3571[32m [repeated 255x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.1907 - loss: 2.5641
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.1907 - loss: 2.5640[32m [repeated 206x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 65ms/step - accuracy: 0.3585 - loss: 1.9399
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 64ms/step - accuracy: 0.3579 - loss: 1.9408
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 64ms/step - accuracy: 0.3573 - loss: 1.9418
[36m(train_cnn_ray_tune pid=2697863)[0m Epoch 6/29
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 97/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 56ms/step - accuracy: 0.2568 - loss: 2.2842
[1m 99/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m26s[0m 56ms/step - accuracy: 0.2569 - loss: 2.2835[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m222/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 46ms/step - accuracy: 0.2088 - loss: 2.3710[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 30ms/step - accuracy: 0.2001 - loss: 2.4256
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 30ms/step - accuracy: 0.2001 - loss: 2.4256[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m443/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2071 - loss: 2.5731
[1m445/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2071 - loss: 2.5730[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  72/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 62ms/step - accuracy: 0.3497 - loss: 1.9562[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m462/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.2780 - loss: 2.1451[32m [repeated 89x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 39ms/step - accuracy: 0.2204 - loss: 2.4612[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 38ms/step - accuracy: 0.2824 - loss: 2.1397 - val_accuracy: 0.3300 - val_loss: 2.1313
[36m(train_cnn_ray_tune pid=2697881)[0m Epoch 18/20
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 117ms/step - accuracy: 0.2812 - loss: 2.1714
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.2986 - loss: 2.1416  
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3407 - loss: 1.9863
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3406 - loss: 1.9868[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m16s[0m 39ms/step - accuracy: 0.3181 - loss: 2.0594[32m [repeated 276x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 31ms/step - accuracy: 0.2370 - loss: 2.2939
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 31ms/step - accuracy: 0.2370 - loss: 2.2939[32m [repeated 188x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m59s[0m 51ms/step - accuracy: 0.1375 - loss: 2.8717 - val_accuracy: 0.2023 - val_loss: 2.4821
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:18[0m 120ms/step - accuracy: 0.2500 - loss: 2.6728
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.2188 - loss: 2.8250  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m192/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 55ms/step - accuracy: 0.2569 - loss: 2.2696
[1m193/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 55ms/step - accuracy: 0.2569 - loss: 2.2695[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 99/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.2796 - loss: 2.1432[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.1896 - loss: 2.5615
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.1896 - loss: 2.5615[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m355/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.2123 - loss: 2.3679
[1m357/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.2123 - loss: 2.3679[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 122/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 58ms/step - accuracy: 0.3400 - loss: 1.9893 [32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m353/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.2123 - loss: 2.3680[32m [repeated 86x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 39ms/step - accuracy: 0.2203 - loss: 2.4613[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 42ms/step - accuracy: 0.2803 - loss: 2.1417 - val_accuracy: 0.3210 - val_loss: 2.1995[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m Epoch 17/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 46ms/step - accuracy: 0.2691 - loss: 2.3497  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.2708 - loss: 2.3156
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  69/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 40ms/step - accuracy: 0.1564 - loss: 2.8556
[1m  70/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 40ms/step - accuracy: 0.1564 - loss: 2.8552
[1m  71/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 40ms/step - accuracy: 0.1564 - loss: 2.8549
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 120/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3403 - loss: 1.9885
[1m 121/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3402 - loss: 1.9889[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m31s[0m 41ms/step - accuracy: 0.1631 - loss: 2.6878[32m [repeated 299x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m37s[0m 47ms/step - accuracy: 0.2544 - loss: 2.2716
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m37s[0m 47ms/step - accuracy: 0.2544 - loss: 2.2716[32m [repeated 189x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 34ms/step - accuracy: 0.2000 - loss: 2.4254 - val_accuracy: 0.2710 - val_loss: 2.2507[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45[0m 91ms/step - accuracy: 0.1250 - loss: 2.4380[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.1875 - loss: 2.2625 
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m288/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.2553 - loss: 2.2642
[1m289/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 54ms/step - accuracy: 0.2553 - loss: 2.2642[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 78/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 38ms/step - accuracy: 0.2927 - loss: 2.1557[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m472/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.2142 - loss: 2.3672
[1m473/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.2142 - loss: 2.3672
[1m474/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.2142 - loss: 2.3672
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 85/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 39ms/step - accuracy: 0.2921 - loss: 2.1542
[1m 86/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 40ms/step - accuracy: 0.2920 - loss: 2.1540
[1m 87/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m19s[0m 40ms/step - accuracy: 0.2919 - loss: 2.1537
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 34ms/step - accuracy: 0.1888 - loss: 2.5601
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 34ms/step - accuracy: 0.1888 - loss: 2.5601[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m481/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.2143 - loss: 2.3672
[1m483/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.2143 - loss: 2.3672[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  37/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.2676 - loss: 2.2439[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m475/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 43ms/step - accuracy: 0.2142 - loss: 2.3672[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3179 - loss: 2.0608 
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3179 - loss: 2.0608
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m264/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.2835 - loss: 2.1463 
[1m265/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.2835 - loss: 2.1463
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 34ms/step - accuracy: 0.1887 - loss: 2.5600[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 56ms/step - accuracy: 0.2067 - loss: 2.5732 - val_accuracy: 0.2583 - val_loss: 2.3075
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 13/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m36s[0m 57ms/step - accuracy: 0.2297 - loss: 2.3182
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m36s[0m 57ms/step - accuracy: 0.2297 - loss: 2.3182
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m36s[0m 57ms/step - accuracy: 0.2297 - loss: 2.3182[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  73/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 67ms/step - accuracy: 0.2680 - loss: 2.2241
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 67ms/step - accuracy: 0.2680 - loss: 2.2236[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m26s[0m 41ms/step - accuracy: 0.1642 - loss: 2.6848[32m [repeated 255x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 206/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m44s[0m 46ms/step - accuracy: 0.1528 - loss: 2.8468
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m43s[0m 46ms/step - accuracy: 0.1527 - loss: 2.8468[32m [repeated 166x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 44ms/step - accuracy: 0.2203 - loss: 2.4613 - val_accuracy: 0.2944 - val_loss: 2.2138
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46[0m 92ms/step - accuracy: 0.2500 - loss: 2.2625[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m377/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 55ms/step - accuracy: 0.2543 - loss: 2.2606
[1m378/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 55ms/step - accuracy: 0.2543 - loss: 2.2605[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m182/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 44ms/step - accuracy: 0.2843 - loss: 2.1602[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m107/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m20s[0m 44ms/step - accuracy: 0.2809 - loss: 2.1664
[1m108/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m20s[0m 44ms/step - accuracy: 0.2809 - loss: 2.1663
[1m109/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m20s[0m 44ms/step - accuracy: 0.2810 - loss: 2.1662
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 31ms/step - accuracy: 0.2355 - loss: 2.2943
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 31ms/step - accuracy: 0.2355 - loss: 2.2943[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m398/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.2848 - loss: 2.1446
[1m400/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.2848 - loss: 2.1446[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 67ms/step - accuracy: 0.2672 - loss: 2.2170[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m404/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.2848 - loss: 2.1445[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m108/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m26s[0m 55ms/step - accuracy: 0.1917 - loss: 2.6121
[1m109/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 55ms/step - accuracy: 0.1917 - loss: 2.6118
[1m110/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 55ms/step - accuracy: 0.1918 - loss: 2.6116
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3178 - loss: 2.0615[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m397/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 55ms/step - accuracy: 0.2542 - loss: 2.2599 
[1m399/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 55ms/step - accuracy: 0.2541 - loss: 2.2599
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 8/27
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 147/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 67ms/step - accuracy: 0.2687 - loss: 2.2119
[1m 148/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 67ms/step - accuracy: 0.2687 - loss: 2.2117[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 49ms/step - accuracy: 0.2151 - loss: 2.3671 - val_accuracy: 0.2899 - val_loss: 2.2520
[36m(train_cnn_ray_tune pid=2697882)[0m Epoch 15/16
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 123ms/step - accuracy: 0.1562 - loss: 2.4268
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 61ms/step - accuracy: 0.1875 - loss: 2.3509  
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 41ms/step - accuracy: 0.2376 - loss: 2.3548
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 41ms/step - accuracy: 0.2376 - loss: 2.3548
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 41ms/step - accuracy: 0.2376 - loss: 2.3548
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m45s[0m 38ms/step - accuracy: 0.1884 - loss: 2.5596 - val_accuracy: 0.2349 - val_loss: 2.2893
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 52ms/step - accuracy: 0.1458 - loss: 2.9475 
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m41s[0m 48ms/step - accuracy: 0.1508 - loss: 2.8457[32m [repeated 254x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m41s[0m 48ms/step - accuracy: 0.1508 - loss: 2.8458
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m41s[0m 48ms/step - accuracy: 0.1508 - loss: 2.8457[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:28[0m 181ms/step - accuracy: 0.1875 - loss: 2.9525
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 38/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.2398 - loss: 2.3262
[1m 39/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.2395 - loss: 2.3262[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m294/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 45ms/step - accuracy: 0.2848 - loss: 2.1553[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 42ms/step - accuracy: 0.2376 - loss: 2.3544
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 42ms/step - accuracy: 0.2376 - loss: 2.3544[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m477/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 55ms/step - accuracy: 0.2536 - loss: 2.2581
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 55ms/step - accuracy: 0.2536 - loss: 2.2581[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 66ms/step - accuracy: 0.2703 - loss: 2.2056[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m537/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 34ms/step - accuracy: 0.2851 - loss: 2.1434[32m [repeated 45x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-07 12:47:22. 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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.3178 - loss: 2.0617[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m355/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.2846 - loss: 2.1542 
[1m357/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.2846 - loss: 2.1542
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m41s[0m 59ms/step - accuracy: 0.3279 - loss: 2.0385
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m41s[0m 59ms/step - accuracy: 0.3279 - loss: 2.0385
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m41s[0m 59ms/step - accuracy: 0.3279 - loss: 2.0386
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 66ms/step - accuracy: 0.2715 - loss: 2.2005
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 66ms/step - accuracy: 0.2715 - loss: 2.2004[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 10/26
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 36ms/step - accuracy: 0.2355 - loss: 2.2938 - val_accuracy: 0.2732 - val_loss: 2.2128
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 11/24
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:04[0m 108ms/step - accuracy: 0.4375 - loss: 2.2128
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 36ms/step - accuracy: 0.3472 - loss: 2.3215  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.2977 - loss: 2.3625
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m544/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 55ms/step - accuracy: 0.2533 - loss: 2.2569
[1m545/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 55ms/step - accuracy: 0.2533 - loss: 2.2569
[1m546/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 55ms/step - accuracy: 0.2533 - loss: 2.2569
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.2851 - loss: 2.1432 - val_accuracy: 0.3329 - val_loss: 2.1180
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m140/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 44ms/step - accuracy: 0.2323 - loss: 2.3383
[1m141/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 44ms/step - accuracy: 0.2322 - loss: 2.3383
[1m142/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 44ms/step - accuracy: 0.2322 - loss: 2.3384
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 32ms/step - accuracy: 0.2023 - loss: 2.4209[32m [repeated 248x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 255/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m58s[0m 65ms/step - accuracy: 0.2719 - loss: 2.1979
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m58s[0m 65ms/step - accuracy: 0.2720 - loss: 2.1978[32m [repeated 229x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 127ms/step - accuracy: 0.3750 - loss: 1.8740
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.3472 - loss: 1.9860  
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 16/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 31ms/step - accuracy: 0.3069 - loss: 2.0542
[1m 18/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 32ms/step - accuracy: 0.3050 - loss: 2.0613[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m154/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 44ms/step - accuracy: 0.2315 - loss: 2.3392[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.3178 - loss: 2.0618
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.3178 - loss: 2.0618[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m414/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 45ms/step - accuracy: 0.2846 - loss: 2.1532
[1m415/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 45ms/step - accuracy: 0.2846 - loss: 2.1531[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m59s[0m 66ms/step - accuracy: 0.2718 - loss: 2.1989 [32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m419/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 45ms/step - accuracy: 0.2846 - loss: 2.1531[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2321 - loss: 2.3139[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m183/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 45ms/step - accuracy: 0.2301 - loss: 2.3410
[1m184/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 45ms/step - accuracy: 0.2301 - loss: 2.3410
[1m185/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 45ms/step - accuracy: 0.2300 - loss: 2.3411
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.2368 - loss: 2.3453 
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.2367 - loss: 2.3453
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 231/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:01[0m 66ms/step - accuracy: 0.2716 - loss: 2.2002
[1m 232/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1:01[0m 66ms/step - accuracy: 0.2716 - loss: 2.2001[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m52s[0m 45ms/step - accuracy: 0.3178 - loss: 2.0618 - val_accuracy: 0.3373 - val_loss: 2.0413[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m Epoch 9/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:51[0m 96ms/step - accuracy: 0.1250 - loss: 2.0298
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m323/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 54ms/step - accuracy: 0.1976 - loss: 2.5847
[1m324/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 54ms/step - accuracy: 0.1976 - loss: 2.5846
[1m325/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 54ms/step - accuracy: 0.1976 - loss: 2.5846
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m18s[0m 57ms/step - accuracy: 0.2320 - loss: 2.3179[32m [repeated 312x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 31ms/step - accuracy: 0.2021 - loss: 2.4194
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2021 - loss: 2.4194[32m [repeated 246x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:13[0m 116ms/step - accuracy: 0.5000 - loss: 1.7842
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.3750 - loss: 2.1313  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 61ms/step - accuracy: 0.2533 - loss: 2.2562 - val_accuracy: 0.3071 - val_loss: 2.2247
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 116ms/step - accuracy: 0.3125 - loss: 2.0356
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 71ms/step - accuracy: 0.2936 - loss: 2.1109
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 68ms/step - accuracy: 0.2899 - loss: 2.1239[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m157/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2797 - loss: 2.1371[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 48ms/step - accuracy: 0.2326 - loss: 2.3132
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 48ms/step - accuracy: 0.2326 - loss: 2.3132[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m520/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 45ms/step - accuracy: 0.2848 - loss: 2.1516
[1m521/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 45ms/step - accuracy: 0.2848 - loss: 2.1516[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 45ms/step - accuracy: 0.2222 - loss: 2.0632 
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m522/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 45ms/step - accuracy: 0.2848 - loss: 2.1516[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 47ms/step - accuracy: 0.2366 - loss: 2.3459[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.2500 - loss: 2.0884  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2676 - loss: 2.1068
[36m(train_cnn_ray_tune pid=2697828)[0m Epoch 18/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m14s[0m 49ms/step - accuracy: 0.2503 - loss: 2.2803
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m14s[0m 49ms/step - accuracy: 0.2503 - loss: 2.2803
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m14s[0m 49ms/step - accuracy: 0.2503 - loss: 2.2803
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 58ms/step - accuracy: 0.2324 - loss: 2.3176[32m [repeated 291x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 43ms/step - accuracy: 0.3174 - loss: 2.0482
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 43ms/step - accuracy: 0.3175 - loss: 2.0480[32m [repeated 246x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 48ms/step - accuracy: 0.2366 - loss: 2.3463
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 48ms/step - accuracy: 0.2366 - loss: 2.3463
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 48ms/step - accuracy: 0.2366 - loss: 2.3463
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 46ms/step - accuracy: 0.2908 - loss: 2.1291 - val_accuracy: 0.3284 - val_loss: 2.2184
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 107ms/step - accuracy: 0.2500 - loss: 2.0845
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 43/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2976 - loss: 2.1194
[1m 45/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2978 - loss: 2.1194[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m100/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 54ms/step - accuracy: 0.2643 - loss: 2.2022[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 42ms/step - accuracy: 0.1666 - loss: 2.6773
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 42ms/step - accuracy: 0.1666 - loss: 2.6773[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m376/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.2264 - loss: 2.3490
[1m378/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.2264 - loss: 2.3490[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m471/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 55ms/step - accuracy: 0.1990 - loss: 2.5798[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.2025 - loss: 2.4180[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 51ms/step - accuracy: 0.2848 - loss: 2.1512 - val_accuracy: 0.3089 - val_loss: 2.2167
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:23[0m 145ms/step - accuracy: 0.3125 - loss: 1.8061
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.2500 - loss: 2.2804 
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.2500 - loss: 2.2804
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m449/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 46ms/step - accuracy: 0.2259 - loss: 2.3503
[1m450/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 46ms/step - accuracy: 0.2259 - loss: 2.3503
[1m451/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 46ms/step - accuracy: 0.2258 - loss: 2.3503
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 16/27
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m21s[0m 49ms/step - accuracy: 0.1498 - loss: 2.8434[32m [repeated 267x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m44s[0m 66ms/step - accuracy: 0.2747 - loss: 2.1829
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m44s[0m 66ms/step - accuracy: 0.2747 - loss: 2.1828[32m [repeated 209x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2027 - loss: 2.4173
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2027 - loss: 2.4173
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2027 - loss: 2.4172
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m185/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 56ms/step - accuracy: 0.2652 - loss: 2.2078
[1m186/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 56ms/step - accuracy: 0.2652 - loss: 2.2079[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m170/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m16s[0m 40ms/step - accuracy: 0.2959 - loss: 2.1262[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.1669 - loss: 2.6760
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.1669 - loss: 2.6760[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m487/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 46ms/step - accuracy: 0.2256 - loss: 2.3507
[1m488/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 46ms/step - accuracy: 0.2256 - loss: 2.3508[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m486/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 46ms/step - accuracy: 0.2256 - loss: 2.3507[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.1669 - loss: 2.6759[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m62s[0m 54ms/step - accuracy: 0.2332 - loss: 2.3124 - val_accuracy: 0.2837 - val_loss: 2.2196
[36m(train_cnn_ray_tune pid=2697885)[0m Epoch 8/25
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:38[0m 137ms/step - accuracy: 0.1875 - loss: 2.7447
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.2292 - loss: 2.5374  
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 58ms/step - accuracy: 0.2333 - loss: 2.3164
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 58ms/step - accuracy: 0.2333 - loss: 2.3164
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 58ms/step - accuracy: 0.2333 - loss: 2.3164
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:25[0m 126ms/step - accuracy: 0.4375 - loss: 2.0888
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m248/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 56ms/step - accuracy: 0.2642 - loss: 2.2131
[1m249/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 56ms/step - accuracy: 0.2642 - loss: 2.2132
[1m250/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 56ms/step - accuracy: 0.2642 - loss: 2.2132
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.3993 - loss: 2.1439 
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.3733 - loss: 2.1897 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.3667 - loss: 2.2064
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.3589 - loss: 2.2240
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 49ms/step - accuracy: 0.3438 - loss: 2.2495 
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.3363 - loss: 2.2616
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m38s[0m 65ms/step - accuracy: 0.2752 - loss: 2.1811[32m [repeated 247x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m16s[0m 49ms/step - accuracy: 0.1496 - loss: 2.8431
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m16s[0m 49ms/step - accuracy: 0.1496 - loss: 2.8431[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 60ms/step - accuracy: 0.1997 - loss: 2.5772 - val_accuracy: 0.2660 - val_loss: 2.2982
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 71ms/step - accuracy: 0.2309 - loss: 2.4278
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 64ms/step - accuracy: 0.2259 - loss: 2.4401[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m274/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 57ms/step - accuracy: 0.2637 - loss: 2.2149[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 49ms/step - accuracy: 0.2498 - loss: 2.2802
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 49ms/step - accuracy: 0.2498 - loss: 2.2802[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m574/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.2830 - loss: 2.1386
[1m575/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.2830 - loss: 2.1386[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.2830 - loss: 2.1386[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 49ms/step - accuracy: 0.2498 - loss: 2.2802[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m62s[0m 53ms/step - accuracy: 0.2365 - loss: 2.3466 - val_accuracy: 0.2793 - val_loss: 2.1551
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 14/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m55s[0m 48ms/step - accuracy: 0.1670 - loss: 2.6756 - val_accuracy: 0.2619 - val_loss: 2.2954
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 141ms/step - accuracy: 0.2500 - loss: 2.1323
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 42ms/step - accuracy: 0.2118 - loss: 2.2536  
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:19[0m 121ms/step - accuracy: 0.3125 - loss: 2.5104[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 41ms/step - accuracy: 0.3021 - loss: 2.4405  
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m290/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 44ms/step - accuracy: 0.2907 - loss: 2.1134
[1m292/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 44ms/step - accuracy: 0.2907 - loss: 2.1134
[1m293/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 44ms/step - accuracy: 0.2907 - loss: 2.1135
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m32s[0m 64ms/step - accuracy: 0.2758 - loss: 2.1793[32m [repeated 316x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 49ms/step - accuracy: 0.1495 - loss: 2.8427
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m11s[0m 49ms/step - accuracy: 0.1495 - loss: 2.8427[32m [repeated 205x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.0764 - loss: 2.5759  
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 52ms/step - accuracy: 0.2251 - loss: 2.3513 - val_accuracy: 0.2871 - val_loss: 2.2436[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m362/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 57ms/step - accuracy: 0.2625 - loss: 2.2188
[1m364/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 57ms/step - accuracy: 0.2625 - loss: 2.2188[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m315/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 44ms/step - accuracy: 0.2908 - loss: 2.1138[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1859 - loss: 2.5474
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1859 - loss: 2.5474[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m444/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 38ms/step - accuracy: 0.2966 - loss: 2.1179
[1m446/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 38ms/step - accuracy: 0.2966 - loss: 2.1178[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m452/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.2966 - loss: 2.1176[32m [repeated 31x across cluster][0m
Trial status: 20 RUNNING
Current time: 2025-11-07 12:47:52. Total running time: 7min 31s
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_8aa9a    RUNNING            2   adam            tanh                                   32                 32                  3                 0          0.00010593          27 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23 │
│ trial_8aa9a    RUNNING            2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18 │
│ trial_8aa9a    RUNNING            2   adam            relu                                   32                 16                  3                 0          0.000139458         20 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25 │
│ trial_8aa9a    RUNNING            2   adam            tanh                                   16                 16                  5                 0          0.000121681         24 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 64                  3                 1          0.000190495         29 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16 │
│ trial_8aa9a    RUNNING            3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27 │
│ trial_8aa9a    RUNNING            3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16 │
│ trial_8aa9a    RUNNING            2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26 │
│ trial_8aa9a    RUNNING            3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17 │
│ trial_8aa9a    RUNNING            3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.2330 - loss: 2.4331[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.1495 - loss: 2.8426 
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 49ms/step - accuracy: 0.1495 - loss: 2.8426
[36m(train_cnn_ray_tune pid=2697874)[0m Epoch 12/18[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m401/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.2623 - loss: 2.2195 
[1m402/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 56ms/step - accuracy: 0.2623 - loss: 2.2195
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 36ms/step - accuracy: 0.2033 - loss: 2.4159 - val_accuracy: 0.2770 - val_loss: 2.2455
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m46s[0m 50ms/step - accuracy: 0.2413 - loss: 2.2911
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m46s[0m 50ms/step - accuracy: 0.2413 - loss: 2.2910
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m46s[0m 50ms/step - accuracy: 0.2413 - loss: 2.2910
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:03[0m 107ms/step - accuracy: 0.0625 - loss: 2.5960
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m20s[0m 41ms/step - accuracy: 0.3192 - loss: 2.0523[32m [repeated 250x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m26s[0m 63ms/step - accuracy: 0.2764 - loss: 2.1778
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m26s[0m 63ms/step - accuracy: 0.2764 - loss: 2.1778[32m [repeated 190x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 258/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m44s[0m 49ms/step - accuracy: 0.2415 - loss: 2.2894
[1m 259/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m44s[0m 49ms/step - accuracy: 0.2415 - loss: 2.2893
[1m 260/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m44s[0m 49ms/step - accuracy: 0.2416 - loss: 2.2893
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m63s[0m 54ms/step - accuracy: 0.2497 - loss: 2.2801 - val_accuracy: 0.3230 - val_loss: 2.1298
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:06[0m 109ms/step - accuracy: 0.3750 - loss: 2.1081
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2368 - loss: 2.2765
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2368 - loss: 2.2765
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2368 - loss: 2.2764
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.2847 - loss: 2.2684 
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.2765 - loss: 2.2579
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m457/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 56ms/step - accuracy: 0.2619 - loss: 2.2207
[1m458/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 55ms/step - accuracy: 0.2619 - loss: 2.2207
[1m459/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 55ms/step - accuracy: 0.2619 - loss: 2.2207
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.2720 - loss: 2.2483
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2676 - loss: 2.2433
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m196/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m20s[0m 52ms/step - accuracy: 0.2086 - loss: 2.5638
[1m198/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 52ms/step - accuracy: 0.2086 - loss: 2.5636[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m209/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.2984 - loss: 2.1384[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2597 - loss: 2.2478
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2568 - loss: 2.2501
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2541 - loss: 2.2514
[1m  12/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2516 - loss: 2.2509
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2484 - loss: 2.2494
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.2477 - loss: 2.2477
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2473 - loss: 2.2459
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2475 - loss: 2.2438
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 35ms/step - accuracy: 0.1862 - loss: 2.5459
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 35ms/step - accuracy: 0.1862 - loss: 2.5459[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m469/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 56ms/step - accuracy: 0.2619 - loss: 2.2209
[1m470/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 56ms/step - accuracy: 0.2619 - loss: 2.2209[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.2978 - loss: 2.1141[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.2480 - loss: 2.2412
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.2486 - loss: 2.2380
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 54ms/step - accuracy: 0.2504 - loss: 2.2324
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 53ms/step - accuracy: 0.2508 - loss: 2.2298 
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 41ms/step - accuracy: 0.2326 - loss: 2.4332[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m Epoch 7/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  60/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 52ms/step - accuracy: 0.2508 - loss: 2.2198
[1m  61/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 52ms/step - accuracy: 0.2507 - loss: 2.2203
[1m  62/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 52ms/step - accuracy: 0.2505 - loss: 2.2208
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 44ms/step - accuracy: 0.2978 - loss: 2.1140 - val_accuracy: 0.3010 - val_loss: 2.2267
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m523/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 55ms/step - accuracy: 0.2618 - loss: 2.2216
[1m524/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 55ms/step - accuracy: 0.2617 - loss: 2.2216
[1m525/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 55ms/step - accuracy: 0.2617 - loss: 2.2216
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m41s[0m 49ms/step - accuracy: 0.2569 - loss: 2.3065
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m41s[0m 49ms/step - accuracy: 0.2569 - loss: 2.3066
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m41s[0m 49ms/step - accuracy: 0.2568 - loss: 2.3067
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 41ms/step - accuracy: 0.3191 - loss: 2.0520[32m [repeated 236x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m39s[0m 49ms/step - accuracy: 0.2428 - loss: 2.2847
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m39s[0m 50ms/step - accuracy: 0.2429 - loss: 2.2847[32m [repeated 150x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m75s[0m 65ms/step - accuracy: 0.2338 - loss: 2.3158 - val_accuracy: 0.3059 - val_loss: 2.2025
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 98ms/step - accuracy: 0.3125 - loss: 2.2056[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 49ms/step - accuracy: 0.1495 - loss: 2.8421
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 49ms/step - accuracy: 0.1495 - loss: 2.8421
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 49ms/step - accuracy: 0.1495 - loss: 2.8421[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.3750 - loss: 2.2144 
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2685 - loss: 2.2846[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 64ms/step - accuracy: 0.2679 - loss: 2.2850
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.2672 - loss: 2.2854[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m292/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 53ms/step - accuracy: 0.2091 - loss: 2.5579
[1m293/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m15s[0m 53ms/step - accuracy: 0.2091 - loss: 2.5579[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m264/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 46ms/step - accuracy: 0.2288 - loss: 2.3298[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 49ms/step - accuracy: 0.1495 - loss: 2.8420
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 49ms/step - accuracy: 0.1495 - loss: 2.8420[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m550/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 44ms/step - accuracy: 0.2913 - loss: 2.1180
[1m551/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 44ms/step - accuracy: 0.2913 - loss: 2.1180[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m562/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 55ms/step - accuracy: 0.2616 - loss: 2.2220[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.2373 - loss: 2.2759[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m Epoch 19/27
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m36s[0m 49ms/step - accuracy: 0.2544 - loss: 2.3115
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m36s[0m 49ms/step - accuracy: 0.2544 - loss: 2.3116
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m36s[0m 49ms/step - accuracy: 0.2544 - loss: 2.3116
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m49s[0m 51ms/step - accuracy: 0.2467 - loss: 2.2488[32m [repeated 244x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m15s[0m 62ms/step - accuracy: 0.2771 - loss: 2.1762
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m15s[0m 62ms/step - accuracy: 0.2771 - loss: 2.1762[32m [repeated 151x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 49ms/step - accuracy: 0.2913 - loss: 2.1185 - val_accuracy: 0.2968 - val_loss: 2.1916
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 17/27
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 93ms/step - accuracy: 0.2188 - loss: 1.9886
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 42ms/step - accuracy: 0.3021 - loss: 2.0083
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 58ms/step - accuracy: 0.2562 - loss: 2.2790 [32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 125/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2563 - loss: 2.2792
[1m 126/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 59ms/step - accuracy: 0.2562 - loss: 2.2791[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.1863 - loss: 2.5452 - val_accuracy: 0.2357 - val_loss: 2.2817
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 10/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.3261 - loss: 2.0699
[1m 11/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 43ms/step - accuracy: 0.3275 - loss: 2.0711[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m388/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 52ms/step - accuracy: 0.2088 - loss: 2.5560 [32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:50[0m 95ms/step - accuracy: 0.3750 - loss: 2.2278
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.2882 - loss: 2.3628 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 45ms/step - accuracy: 0.2591 - loss: 2.3827
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 40ms/step - accuracy: 0.3195 - loss: 2.0508
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 40ms/step - accuracy: 0.3195 - loss: 2.0507[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m390/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 45ms/step - accuracy: 0.2269 - loss: 2.3322
[1m391/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 45ms/step - accuracy: 0.2269 - loss: 2.3322[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m511/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 35ms/step - accuracy: 0.2937 - loss: 2.1341[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 25/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 41ms/step - accuracy: 0.3158 - loss: 2.1059
[1m 26/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 41ms/step - accuracy: 0.3151 - loss: 2.1068
[1m 28/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 40ms/step - accuracy: 0.3140 - loss: 2.1079
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.3646 - loss: 2.3453  
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 40ms/step - accuracy: 0.3196 - loss: 2.0505[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m32s[0m 48ms/step - accuracy: 0.2531 - loss: 2.3146
[1m 476/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m32s[0m 48ms/step - accuracy: 0.2530 - loss: 2.3146
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m32s[0m 48ms/step - accuracy: 0.2530 - loss: 2.3147
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.2500 - loss: 2.9846 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.2422 - loss: 2.9588
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.2449 - loss: 2.3114 
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.2449 - loss: 2.3114
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 48ms/step - accuracy: 0.1741 - loss: 2.8736[32m [repeated 274x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 125/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 33ms/step - accuracy: 0.1840 - loss: 2.5183
[1m 127/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 33ms/step - accuracy: 0.1840 - loss: 2.5181[32m [repeated 213x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 62ms/step - accuracy: 0.2615 - loss: 2.2222 - val_accuracy: 0.2948 - val_loss: 2.2056
[36m(train_cnn_ray_tune pid=2697871)[0m Epoch 8/17[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:22[0m 123ms/step - accuracy: 0.3125 - loss: 1.9515
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 38ms/step - accuracy: 0.3125 - loss: 2.0550  
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.2074 - loss: 2.9432 
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m309/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.3057 - loss: 2.0799 
[1m310/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.3057 - loss: 2.0800
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 57ms/step - accuracy: 0.2338 - loss: 2.9573
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.2193 - loss: 2.9552
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m63s[0m 54ms/step - accuracy: 0.1495 - loss: 2.8420 - val_accuracy: 0.2031 - val_loss: 2.4589[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m130/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 42ms/step - accuracy: 0.2996 - loss: 2.1145
[1m131/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 42ms/step - accuracy: 0.2995 - loss: 2.1145[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 91/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 52ms/step - accuracy: 0.2697 - loss: 2.1991[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:13[0m 116ms/step - accuracy: 0.3125 - loss: 3.0898[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.2934 - loss: 2.1332 - val_accuracy: 0.3248 - val_loss: 2.1292
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 62ms/step - accuracy: 0.2773 - loss: 2.1753
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 62ms/step - accuracy: 0.2773 - loss: 2.1753[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m515/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 44ms/step - accuracy: 0.2259 - loss: 2.3342
[1m517/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 44ms/step - accuracy: 0.2258 - loss: 2.3342[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m324/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.3055 - loss: 2.0804[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m222/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 37ms/step - accuracy: 0.3070 - loss: 2.0758
[1m223/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 37ms/step - accuracy: 0.3070 - loss: 2.0759
[1m224/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 37ms/step - accuracy: 0.3069 - loss: 2.0760
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 317ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 5/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step  
[1m10/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m16/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m24/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 44ms/step - accuracy: 0.2454 - loss: 2.3108[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m37/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m27s[0m 47ms/step - accuracy: 0.2512 - loss: 2.3177
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m27s[0m 47ms/step - accuracy: 0.2512 - loss: 2.3178
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m27s[0m 47ms/step - accuracy: 0.2512 - loss: 2.3178[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m40/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m44/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m57/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m64/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step
[1m72/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m77/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 13ms/step
[1m83/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 57ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m  5/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step
[1m  8/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 11/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[1m 13/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 69ms/step - accuracy: 0.2292 - loss: 2.1338 
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 16/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[1m 19/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:17[0m 67ms/step - accuracy: 0.2539 - loss: 2.0761
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 65ms/step - accuracy: 0.2706 - loss: 2.0401
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 22/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 26/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 19ms/step
[1m 32/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 69ms/step - accuracy: 0.2811 - loss: 2.0179
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 68ms/step - accuracy: 0.2868 - loss: 2.0061
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 37/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 42/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.2999 - loss: 1.9897
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.3036 - loss: 1.9892
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 47/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 52/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3055 - loss: 1.9924
[1m  12/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3056 - loss: 1.9970
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 58/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 63/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 68/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.3073 - loss: 1.9967
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.3089 - loss: 1.9959
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 73/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 78/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[1m 84/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 65ms/step - accuracy: 0.3097 - loss: 1.9968
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 64ms/step - accuracy: 0.3111 - loss: 1.9969
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.3123 - loss: 1.9976
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 89/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m 93/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 65ms/step - accuracy: 0.3129 - loss: 1.9985
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m 97/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697881)[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=2697881)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697835)[0m 2025-11-07 12:40:25.067062: 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=2697835)[0m 2025-11-07 12:40:25.088396: 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=2697835)[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=2697835)[0m E0000 00:00:1762515625.116037 2699155 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=2697835)[0m E0000 00:00:1762515625.124090 2699155 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=2697835)[0m W0000 00:00:1762515625.143585 2699155 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=2697835)[0m 2025-11-07 12:40:25.149374: 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=2697835)[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=2697872)[0m 2025-11-07 12:40:28.305938: 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=2697872)[0m 2025-11-07 12:40:28.306021: 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=2697872)[0m 2025-11-07 12:40:28.306031: 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=2697872)[0m 2025-11-07 12:40:28.306036: 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=2697872)[0m 2025-11-07 12:40:28.306041: 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=2697872)[0m 2025-11-07 12:40:28.306045: 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=2697872)[0m 2025-11-07 12:40:28.306328: 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=2697872)[0m 2025-11-07 12:40:28.306368: 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=2697872)[0m 2025-11-07 12:40:28.306373: 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=2697881)[0m 
[1m102/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 13ms/step
[1m106/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 65ms/step - accuracy: 0.3139 - loss: 1.9982
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.3147 - loss: 1.9992
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.3158 - loss: 1.9994
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m110/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 13ms/step
[1m116/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.3168 - loss: 1.9998
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m120/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.3179 - loss: 2.0000
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 64ms/step - accuracy: 0.3190 - loss: 1.9998
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m125/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 64ms/step - accuracy: 0.3200 - loss: 1.9993
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m129/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 13ms/step
[1m134/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.3209 - loss: 1.9998
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.3215 - loss: 2.0005
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m137/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 13ms/step
[1m141/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3220 - loss: 2.0008
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3222 - loss: 2.0014
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m146/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 13ms/step
[1m150/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.3223 - loss: 2.0024
[1m  31/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3222 - loss: 2.0034
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m22s[0m 43ms/step - accuracy: 0.1793 - loss: 2.6092[32m [repeated 237x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 153/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 48ms/step - accuracy: 0.1592 - loss: 2.8644
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 48ms/step - accuracy: 0.1591 - loss: 2.8644[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m154/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 13ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  32/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 63ms/step - accuracy: 0.3221 - loss: 2.0042
[36m(train_cnn_ray_tune pid=2697863)[0m Epoch 7/29
[36m(train_cnn_ray_tune pid=2697881)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  34/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.3218 - loss: 2.0056

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:48:16. Total running time: 7min 55s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             471.914 │
│ time_total_s                 471.914 │
│ training_iteration                 1 │
│ val_accuracy                  0.3248 │
╰──────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  36/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.3217 - loss: 2.0065

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:48:16. Total running time: 7min 55s
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  37/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.3216 - loss: 2.0067
[1m  38/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.3217 - loss: 2.0070
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  39/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 61ms/step - accuracy: 0.3218 - loss: 2.0071
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  40/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 62ms/step - accuracy: 0.3217 - loss: 2.0074
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m77s[0m 67ms/step - accuracy: 0.3235 - loss: 2.0478 - val_accuracy: 0.3296 - val_loss: 2.1571
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  41/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.3216 - loss: 2.0078
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  42/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.3217 - loss: 2.0079
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m173/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m21s[0m 53ms/step - accuracy: 0.2705 - loss: 2.1918
[1m175/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 53ms/step - accuracy: 0.2705 - loss: 2.1918[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m186/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m20s[0m 53ms/step - accuracy: 0.2706 - loss: 2.1917[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3:08[0m 164ms/step - accuracy: 0.1250 - loss: 2.3455
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  43/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.3218 - loss: 2.0080
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  44/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.3218 - loss: 2.0081
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  45/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 62ms/step - accuracy: 0.3218 - loss: 2.0082
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.3218 - loss: 2.0083
[1m  47/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.3218 - loss: 2.0081
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.3217 - loss: 2.0082
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.3217 - loss: 2.0084
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 62ms/step - accuracy: 0.2775 - loss: 2.1747
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 62ms/step - accuracy: 0.2775 - loss: 2.1747[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m462/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 37ms/step - accuracy: 0.3050 - loss: 2.0830
[1m464/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 37ms/step - accuracy: 0.3050 - loss: 2.0830[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m456/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 37ms/step - accuracy: 0.3050 - loss: 2.0830[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.3217 - loss: 2.0086
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.3217 - loss: 2.0086
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 63ms/step - accuracy: 0.3217 - loss: 2.0087
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 63ms/step - accuracy: 0.3216 - loss: 2.0090
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 62ms/step - accuracy: 0.3215 - loss: 2.0094
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.3216 - loss: 2.0099
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 61ms/step - accuracy: 0.3216 - loss: 2.0102
[1m  60/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 60ms/step - accuracy: 0.3217 - loss: 2.0107
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 44ms/step - accuracy: 0.2459 - loss: 2.3104[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  62/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.3217 - loss: 2.0111
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  63/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.3217 - loss: 2.0113
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m25s[0m 48ms/step - accuracy: 0.2461 - loss: 2.2776
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m24s[0m 48ms/step - accuracy: 0.2461 - loss: 2.2776
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m24s[0m 48ms/step - accuracy: 0.2461 - loss: 2.2776[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  64/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.3217 - loss: 2.0116
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  65/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.3217 - loss: 2.0118
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 50ms/step - accuracy: 0.2255 - loss: 2.3351 - val_accuracy: 0.2881 - val_loss: 2.2322
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  66/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 60ms/step - accuracy: 0.3217 - loss: 2.0121
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  68/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.3216 - loss: 2.0127
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  70/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.3214 - loss: 2.0133
[1m  71/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.3213 - loss: 2.0137
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  72/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.3213 - loss: 2.0141
[1m  73/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.3212 - loss: 2.0144
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  74/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.3212 - loss: 2.0146
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 59ms/step - accuracy: 0.3211 - loss: 2.0149
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 452ms/step
[1m 5/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step  
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 60ms/step - accuracy: 0.3211 - loss: 2.0151
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3210 - loss: 2.0157
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 9/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m13/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3210 - loss: 2.0160
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3210 - loss: 2.0162
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m17/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m22/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3210 - loss: 2.0167
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m25/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3210 - loss: 2.0171
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3211 - loss: 2.0173
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m32/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3211 - loss: 2.0174
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m37/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3212 - loss: 2.0175
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3212 - loss: 2.0176
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m45/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  89/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3213 - loss: 2.0177
[1m  90/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3214 - loss: 2.0178
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 16ms/step
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  91/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3214 - loss: 2.0179
[1m  92/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3215 - loss: 2.0180
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m64/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  93/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3215 - loss: 2.0181
[1m  94/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3216 - loss: 2.0183
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  95/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3216 - loss: 2.0184
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m71/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  96/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3216 - loss: 2.0186
[1m  97/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3217 - loss: 2.0188
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 15/28
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m79/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 16ms/step
[1m83/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  98/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3217 - loss: 2.0190
[1m  99/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3218 - loss: 2.0191
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 109ms/step - accuracy: 0.0625 - loss: 3.0886
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.1094 - loss: 2.9519  
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 100/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3218 - loss: 2.0193
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3218 - loss: 2.0194
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3218 - loss: 2.0195
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3219 - loss: 2.0196
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3219 - loss: 2.0196
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3220 - loss: 2.0197
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 20ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3220 - loss: 2.0199
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3220 - loss: 2.0200
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3220 - loss: 2.0202
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3220 - loss: 2.0204
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3220 - loss: 2.0205
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 59ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3220 - loss: 2.0207
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3220 - loss: 2.0209
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m  5/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 10/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3220 - loss: 2.0210
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3220 - loss: 2.0212
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 14/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 19/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[1m 23/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3220 - loss: 2.0215
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 27/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 32/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 117/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3220 - loss: 2.0217
[1m 118/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3220 - loss: 2.0219
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 119/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3220 - loss: 2.0221
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m17s[0m 42ms/step - accuracy: 0.1777 - loss: 2.6130[32m [repeated 263x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m41s[0m 47ms/step - accuracy: 0.1545 - loss: 2.8623
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m41s[0m 47ms/step - accuracy: 0.1545 - loss: 2.8622[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 36/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[1m 40/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 120/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3220 - loss: 2.0222
[1m 121/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3219 - loss: 2.0224
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 44/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 48/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 53/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 123/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 58ms/step - accuracy: 0.3219 - loss: 2.0227
[1m 124/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 58ms/step - accuracy: 0.3218 - loss: 2.0229 
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 58/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[1m 63/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 67/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[1m 72/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m53s[0m 46ms/step - accuracy: 0.3206 - loss: 2.0477 - val_accuracy: 0.3439 - val_loss: 2.0754
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 76/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[1m 80/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 83/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 13ms/step
[1m 87/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m288/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 52ms/step - accuracy: 0.2709 - loss: 2.1923
[1m290/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 51ms/step - accuracy: 0.2709 - loss: 2.1923[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 40/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.1910 - loss: 2.5782[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m 93/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m 98/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m102/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 13ms/step
[1m105/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m108/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 14ms/step
[1m112/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m117/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 14ms/step
[1m121/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 14ms/step

Trial status: 19 RUNNING | 1 TERMINATED
Current time: 2025-11-07 12:48:22. Total running time: 8min 1s
Logical resource usage: 19.0/20 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_8aa9a    RUNNING              2   adam            tanh                                   32                 32                  3                 0          0.00010593          27                                              │
│ trial_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000190495         29                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.2094 - loss: 2.3974
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.2094 - loss: 2.3973[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[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=2697882)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m393/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 41ms/step - accuracy: 0.2967 - loss: 2.1129
[1m395/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 41ms/step - accuracy: 0.2967 - loss: 2.1129[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m391/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 41ms/step - accuracy: 0.2967 - loss: 2.1129[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m126/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 14ms/step
[1m129/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m133/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 14ms/step
[1m138/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m142/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m147/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 14ms/step
[1m152/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697882)[0m 
[1m157/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 29ms/step - accuracy: 0.2094 - loss: 2.3973[32m [repeated 71x across cluster][0m

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:48:22. Total running time: 8min 1s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             478.719 │
│ time_total_s                 478.719 │
│ training_iteration                 1 │
│ val_accuracy                 0.28807 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:48:22. Total running time: 8min 1s
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m29s[0m 39ms/step - accuracy: 0.2422 - loss: 2.3815
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m29s[0m 39ms/step - accuracy: 0.2422 - loss: 2.3815
[1m 393/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m29s[0m 39ms/step - accuracy: 0.2422 - loss: 2.3815[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m34s[0m 58ms/step - accuracy: 0.2087 - loss: 2.5517 - val_accuracy: 0.2662 - val_loss: 2.2874
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.3053 - loss: 2.0837 - val_accuracy: 0.3208 - val_loss: 2.2354
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:18[0m 137ms/step - accuracy: 0.2500 - loss: 2.2472
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 33ms/step - accuracy: 0.2882 - loss: 2.0653  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.2535 - loss: 2.1054
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 9/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44[0m 90ms/step - accuracy: 0.3750 - loss: 2.2596
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 41ms/step - accuracy: 0.3542 - loss: 2.1084 
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m12s[0m 46ms/step - accuracy: 0.2493 - loss: 2.3197[32m [repeated 284x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.2503 - loss: 2.2504
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.2503 - loss: 2.2504[32m [repeated 248x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m56s[0m 48ms/step - accuracy: 0.2460 - loss: 2.3102 - val_accuracy: 0.2773 - val_loss: 2.2094
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 79/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.3067 - loss: 2.0777
[1m 81/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.3069 - loss: 2.0777[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m160/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 43ms/step - accuracy: 0.2050 - loss: 2.5319[32m [repeated 68x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.1764 - loss: 2.6162
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.1764 - loss: 2.6162[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m407/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.2708 - loss: 2.1933
[1m408/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 50ms/step - accuracy: 0.2708 - loss: 2.1933[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m523/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.2963 - loss: 2.1132[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 41ms/step - accuracy: 0.1764 - loss: 2.6164[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.2475 - loss: 2.2751 
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.2475 - loss: 2.2751
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.2476 - loss: 2.2461
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.2476 - loss: 2.2461
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.2476 - loss: 2.2461
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m79s[0m 69ms/step - accuracy: 0.2778 - loss: 2.1741 - val_accuracy: 0.3333 - val_loss: 2.1083
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.3750 - loss: 2.1747 
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.3611 - loss: 2.2188
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.3529 - loss: 2.2205
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.3423 - loss: 2.2301
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.3425 - loss: 2.2267
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.3459 - loss: 2.2193
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.3505 - loss: 2.2046
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.3540 - loss: 2.1905
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.3555 - loss: 2.1799
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:38[0m 137ms/step - accuracy: 0.3750 - loss: 2.0016[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.3567 - loss: 2.1709
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  12/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.3574 - loss: 2.1642
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:50[0m 96ms/step - accuracy: 0.2500 - loss: 2.3196
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.2465 - loss: 2.3051 
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.3573 - loss: 2.1602
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.3566 - loss: 2.1570
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.3553 - loss: 2.1556
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 63ms/step - accuracy: 0.3551 - loss: 2.1527
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m46s[0m 53ms/step - accuracy: 0.3213 - loss: 2.0250
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m46s[0m 53ms/step - accuracy: 0.3213 - loss: 2.0250
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m45s[0m 53ms/step - accuracy: 0.3213 - loss: 2.0250
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3554 - loss: 2.1502
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3561 - loss: 2.1462
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 62ms/step - accuracy: 0.3568 - loss: 2.1424
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.3572 - loss: 2.1389
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 60ms/step - accuracy: 0.3574 - loss: 2.1336
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.3567 - loss: 2.1297
[36m(train_cnn_ray_tune pid=2697874)[0m Epoch 13/18[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.3560 - loss: 2.1286
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.3552 - loss: 2.1275
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 59ms/step - accuracy: 0.3542 - loss: 2.1268
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 59ms/step - accuracy: 0.3532 - loss: 2.1262
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.3510 - loss: 2.1247
[1m  31/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.3500 - loss: 2.1240
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  32/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.3489 - loss: 2.1237
[1m  33/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.3479 - loss: 2.1234
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  34/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.3469 - loss: 2.1230
[1m  36/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.3449 - loss: 2.1227
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  37/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.3440 - loss: 2.1225
[1m  38/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.3433 - loss: 2.1222
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  39/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.3426 - loss: 2.1217
[1m  40/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.3419 - loss: 2.1214
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  41/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 58ms/step - accuracy: 0.3412 - loss: 2.1212
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  43/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3399 - loss: 2.1209
[1m  44/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.3393 - loss: 2.1207
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  45/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.3388 - loss: 2.1206
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3382 - loss: 2.1204
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m  62/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 30ms/step - accuracy: 0.2403 - loss: 2.3299[32m [repeated 272x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m28s[0m 44ms/step - accuracy: 0.1515 - loss: 2.8506
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m27s[0m 44ms/step - accuracy: 0.1515 - loss: 2.8505[32m [repeated 223x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  47/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.3375 - loss: 2.1203
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.3369 - loss: 2.1203
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3363 - loss: 2.1202
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3357 - loss: 2.1202
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3346 - loss: 2.1200
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3336 - loss: 2.1199
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3331 - loss: 2.1199
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3326 - loss: 2.1199
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3320 - loss: 2.1201
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3315 - loss: 2.1202
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3310 - loss: 2.1203
[1m  60/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3304 - loss: 2.1205
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m215/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.3112 - loss: 2.0691
[1m217/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.3112 - loss: 2.0691[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m221/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.3112 - loss: 2.0691[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  61/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.3299 - loss: 2.1207
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  63/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3288 - loss: 2.1211
[1m  64/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.3282 - loss: 2.1213
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  65/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.3276 - loss: 2.1216
[1m  66/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.3270 - loss: 2.1219
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  67/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.3264 - loss: 2.1223
[1m  68/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.3259 - loss: 2.1225
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2475 - loss: 2.2478
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2475 - loss: 2.2478[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m505/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 50ms/step - accuracy: 0.2708 - loss: 2.1940
[1m507/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 50ms/step - accuracy: 0.2708 - loss: 2.1940[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m500/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 50ms/step - accuracy: 0.2708 - loss: 2.1940[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 46ms/step - accuracy: 0.2961 - loss: 2.1132 - val_accuracy: 0.3115 - val_loss: 2.1880
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  69/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.3254 - loss: 2.1226
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  70/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3250 - loss: 2.1226
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  71/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3246 - loss: 2.1226
[1m  72/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3243 - loss: 2.1225
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.3316 - loss: 2.1653  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 38ms/step - accuracy: 0.3377 - loss: 2.1160
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  73/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3239 - loss: 2.1225
[1m  74/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3236 - loss: 2.1225
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 41ms/step - accuracy: 0.1759 - loss: 2.6177[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 58ms/step - accuracy: 0.3229 - loss: 2.1225
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.3225 - loss: 2.1224
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.2491 - loss: 2.3201 
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.2491 - loss: 2.3201
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3222 - loss: 2.1222
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m519/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 50ms/step - accuracy: 0.2708 - loss: 2.1941
[1m520/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 50ms/step - accuracy: 0.2708 - loss: 2.1941
[1m521/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 50ms/step - accuracy: 0.2708 - loss: 2.1942
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3216 - loss: 2.1219
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 59ms/step - accuracy: 0.3213 - loss: 2.1218
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3210 - loss: 2.1216
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3207 - loss: 2.1215
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3205 - loss: 2.1213
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3202 - loss: 2.1211
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 33ms/step - accuracy: 0.2095 - loss: 2.3971 - val_accuracy: 0.2662 - val_loss: 2.2467
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3200 - loss: 2.1209
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3198 - loss: 2.1207
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3196 - loss: 2.1205
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  90/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3193 - loss: 2.1200
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  91/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3192 - loss: 2.1197
[1m  92/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3190 - loss: 2.1194
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  93/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 58ms/step - accuracy: 0.3189 - loss: 2.1191
[1m  94/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3187 - loss: 2.1188
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  95/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 58ms/step - accuracy: 0.3186 - loss: 2.1185
[1m  96/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3184 - loss: 2.1182
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  97/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3183 - loss: 2.1179
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 129ms/step - accuracy: 0.3750 - loss: 2.1120
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  98/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3182 - loss: 2.1176
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  99/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3181 - loss: 2.1173
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 100/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3180 - loss: 2.1170
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3179 - loss: 2.1167
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3178 - loss: 2.1164
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3177 - loss: 2.1161
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3175 - loss: 2.1158
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3174 - loss: 2.1155
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3173 - loss: 2.1153
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3172 - loss: 2.1150
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3171 - loss: 2.1147
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3170 - loss: 2.1145
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3168 - loss: 2.1143
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 18/27
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3167 - loss: 2.1141
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 59ms/step - accuracy: 0.3166 - loss: 2.1139
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3163 - loss: 2.1135
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3162 - loss: 2.1134
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3161 - loss: 2.1133
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 117/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3159 - loss: 2.1132
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 118/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3158 - loss: 2.1131
[1m 119/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3156 - loss: 2.1130
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 120/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 59ms/step - accuracy: 0.3155 - loss: 2.1130
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 121/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3153 - loss: 2.1129
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 122/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3152 - loss: 2.1128
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 123/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3150 - loss: 2.1128
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 124/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3149 - loss: 2.1127
[1m 125/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3147 - loss: 2.1127
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 126/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3146 - loss: 2.1128
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 127/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3145 - loss: 2.1128
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3143 - loss: 2.1128
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 38ms/step - accuracy: 0.2394 - loss: 2.3882[32m [repeated 276x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m41s[0m 55ms/step - accuracy: 0.3237 - loss: 2.0219
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m41s[0m 55ms/step - accuracy: 0.3238 - loss: 2.0218[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3142 - loss: 2.1128
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3140 - loss: 2.1128
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3139 - loss: 2.1128
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3138 - loss: 2.1128
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3137 - loss: 2.1128
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3136 - loss: 2.1128
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3135 - loss: 2.1127
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3134 - loss: 2.1127
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 60ms/step - accuracy: 0.3133 - loss: 2.1127
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3133 - loss: 2.1126
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3132 - loss: 2.1126
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3131 - loss: 2.1126
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3130 - loss: 2.1125
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m362/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 47ms/step - accuracy: 0.2083 - loss: 2.5260
[1m364/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.2083 - loss: 2.5260 [32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m361/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 47ms/step - accuracy: 0.2083 - loss: 2.5260[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3130 - loss: 2.1124
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3129 - loss: 2.1123
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 144/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3128 - loss: 2.1123
[1m 145/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3128 - loss: 2.1122
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 147/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3127 - loss: 2.1121
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 149/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3126 - loss: 2.1119
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 150/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3125 - loss: 2.1118
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.1856 - loss: 2.5191
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 33ms/step - accuracy: 0.1857 - loss: 2.5191[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m371/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.3121 - loss: 2.0690
[1m373/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.3121 - loss: 2.0690[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m375/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.2083 - loss: 2.5259[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 151/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3125 - loss: 2.1118
[1m 152/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3124 - loss: 2.1117
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 153/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3124 - loss: 2.1116
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 60ms/step - accuracy: 0.3124 - loss: 2.1115
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 60ms/step - accuracy: 0.3123 - loss: 2.1114 
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 30ms/step - accuracy: 0.2472 - loss: 2.2491[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m38s[0m 55ms/step - accuracy: 0.3243 - loss: 2.0213
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m38s[0m 55ms/step - accuracy: 0.3243 - loss: 2.0213
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m38s[0m 55ms/step - accuracy: 0.3243 - loss: 2.0212
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.2472 - loss: 2.2492
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 30ms/step - accuracy: 0.2472 - loss: 2.2492
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 30ms/step - accuracy: 0.2472 - loss: 2.2492
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 57ms/step - accuracy: 0.2707 - loss: 2.1949 - val_accuracy: 0.3034 - val_loss: 2.2113
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 15/28
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 138ms/step - accuracy: 0.3438 - loss: 2.2119
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.3359 - loss: 2.1943  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 48ms/step - accuracy: 0.3177 - loss: 2.2104
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m54s[0m 58ms/step - accuracy: 0.3109 - loss: 2.1075[32m [repeated 224x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m17s[0m 44ms/step - accuracy: 0.1511 - loss: 2.8444
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m17s[0m 44ms/step - accuracy: 0.1511 - loss: 2.8444[32m [repeated 191x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m52s[0m 45ms/step - accuracy: 0.1757 - loss: 2.6187 - val_accuracy: 0.2511 - val_loss: 2.2910
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 40/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 48ms/step - accuracy: 0.2894 - loss: 2.1687
[1m 41/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 49ms/step - accuracy: 0.2892 - loss: 2.1690[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 39/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 48ms/step - accuracy: 0.2895 - loss: 2.1683[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 41ms/step - accuracy: 0.1667 - loss: 3.0318  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.1856 - loss: 2.9101
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 33ms/step - accuracy: 0.1863 - loss: 2.5188
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 33ms/step - accuracy: 0.1863 - loss: 2.5188[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m513/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 35ms/step - accuracy: 0.3116 - loss: 2.0703
[1m514/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 35ms/step - accuracy: 0.3116 - loss: 2.0703[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m486/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 46ms/step - accuracy: 0.2091 - loss: 2.5250[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 33ms/step - accuracy: 0.1864 - loss: 2.5188[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:22[0m 124ms/step - accuracy: 0.1875 - loss: 2.3281
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:21[0m 71ms/step - accuracy: 0.2031 - loss: 2.3247 
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1979 - loss: 2.3251
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.1953 - loss: 2.3200
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 61ms/step - accuracy: 0.1937 - loss: 2.3252
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1866 - loss: 2.3445
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 49ms/step - accuracy: 0.1893 - loss: 2.3515 
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 50ms/step - accuracy: 0.1904 - loss: 2.3542
[36m(train_cnn_ray_tune pid=2697835)[0m Epoch 9/16[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:49[0m 95ms/step - accuracy: 0.2500 - loss: 2.3550[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.1865 - loss: 2.5187
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.1865 - loss: 2.5187
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 33ms/step - accuracy: 0.1865 - loss: 2.5186
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m48s[0m 57ms/step - accuracy: 0.3091 - loss: 2.1068[32m [repeated 259x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.1511 - loss: 2.8419
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 44ms/step - accuracy: 0.1511 - loss: 2.8419[32m [repeated 181x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m39s[0m 34ms/step - accuracy: 0.2473 - loss: 2.2494 - val_accuracy: 0.2956 - val_loss: 2.1938[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m339/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.2995 - loss: 2.1152 
[1m341/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.2995 - loss: 2.1151
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m139/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 50ms/step - accuracy: 0.2826 - loss: 2.1715
[1m140/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 50ms/step - accuracy: 0.2825 - loss: 2.1716[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m141/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 50ms/step - accuracy: 0.2825 - loss: 2.1717[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.2188 - loss: 2.3734  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 33ms/step - accuracy: 0.2081 - loss: 2.4164
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.2523 - loss: 2.2493
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 47ms/step - accuracy: 0.2523 - loss: 2.2493[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m571/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 47ms/step - accuracy: 0.2096 - loss: 2.5247
[1m572/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 47ms/step - accuracy: 0.2096 - loss: 2.5247[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m356/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.2995 - loss: 2.1148[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.3113 - loss: 2.0710 - val_accuracy: 0.3127 - val_loss: 2.2225
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 47ms/step - accuracy: 0.2523 - loss: 2.2492[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 391ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 4/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 19ms/step  
[1m 8/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[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=2697828)[0m 
[1m17/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 18ms/step
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m24/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m27/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m30/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m33/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[1m38/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 28ms/step - accuracy: 0.2118 - loss: 2.3902 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.2190 - loss: 2.3778
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 17ms/step
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 16ms/step
[1m62/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m69/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 16ms/step
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m77/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 16ms/step
[1m81/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m84/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[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=2697880)[0m Epoch 13/24
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 50ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m  5/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m  9/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:04[0m 108ms/step - accuracy: 0.2500 - loss: 2.2892
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 13/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step
[1m 16/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 20/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 25/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 28/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 30ms/step - accuracy: 0.2231 - loss: 2.3695
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 30ms/step - accuracy: 0.2231 - loss: 2.3695
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 30ms/step - accuracy: 0.2231 - loss: 2.3695
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 12/26
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m204/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 51ms/step - accuracy: 0.2798 - loss: 2.1750
[1m205/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 51ms/step - accuracy: 0.2797 - loss: 2.1750
[1m206/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 51ms/step - accuracy: 0.2797 - loss: 2.1750
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 33/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 39/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:39[0m 86ms/step - accuracy: 0.2500 - loss: 2.4623
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m48s[0m 42ms/step - accuracy: 0.2326 - loss: 2.4590 
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 42/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 46/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 50/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 53/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 57/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 62/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 66/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 70/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 74/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 76/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 79/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 82/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 86/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 151/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 31ms/step - accuracy: 0.2606 - loss: 2.2668[32m [repeated 281x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m43s[0m 57ms/step - accuracy: 0.3069 - loss: 2.1096
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m43s[0m 57ms/step - accuracy: 0.3069 - loss: 2.1096[32m [repeated 235x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 90/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 93/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m 96/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m101/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[1m104/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m106/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 16ms/step
[1m109/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m113/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 16ms/step
[1m117/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m44s[0m 38ms/step - accuracy: 0.1865 - loss: 2.5186 - val_accuracy: 0.2400 - val_loss: 2.2809
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m120/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 16ms/step
[1m124/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m234/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 51ms/step - accuracy: 0.2786 - loss: 2.1759
[1m235/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 51ms/step - accuracy: 0.2785 - loss: 2.1759
[1m236/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 51ms/step - accuracy: 0.2785 - loss: 2.1759
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m129/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 16ms/step
[1m132/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m135/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 24/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 48ms/step - accuracy: 0.2410 - loss: 2.4027
[1m 25/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 48ms/step - accuracy: 0.2409 - loss: 2.4033[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 26/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 50ms/step - accuracy: 0.2409 - loss: 2.4038[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m139/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m142/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m146/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m149/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 16ms/step

Trial status: 18 RUNNING | 2 TERMINATED
Current time: 2025-11-07 12:48:52. Total running time: 8min 31s
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_8aa9a    RUNNING              2   adam            tanh                                   32                 32                  3                 0          0.00010593          27                                              │
│ trial_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000190495         29                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m153/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step
[1m156/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697828)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 16ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:48:52. Total running time: 8min 31s
[36m(train_cnn_ray_tune pid=2697828)[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=2697828)[0m   _log_deprecation_warning(
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             508.556 │
│ time_total_s                 508.556 │
│ training_iteration                 1 │
│ val_accuracy                 0.31269 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:48:52. Total running time: 8min 31s
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 55ms/step - accuracy: 0.2463 - loss: 2.2848
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m9s[0m 55ms/step - accuracy: 0.2463 - loss: 2.2848[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m476/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 42ms/step - accuracy: 0.2999 - loss: 2.1116
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 42ms/step - accuracy: 0.2999 - loss: 2.1115[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m475/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 42ms/step - accuracy: 0.2999 - loss: 2.1116[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.2096 - loss: 2.5246 - val_accuracy: 0.2694 - val_loss: 2.2785
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 55ms/step - accuracy: 0.2463 - loss: 2.2848[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 231/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 31ms/step - accuracy: 0.2597 - loss: 2.2599
[1m 233/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 31ms/step - accuracy: 0.2597 - loss: 2.2598
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m28s[0m 31ms/step - accuracy: 0.2596 - loss: 2.2597[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 16/28
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.2812 - loss: 2.1450
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m37s[0m 57ms/step - accuracy: 0.3052 - loss: 2.1114[32m [repeated 240x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 35ms/step - accuracy: 0.1892 - loss: 2.4940
[1m 172/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 35ms/step - accuracy: 0.1892 - loss: 2.4938[32m [repeated 198x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m61s[0m 52ms/step - accuracy: 0.2525 - loss: 2.2489 - val_accuracy: 0.3306 - val_loss: 2.0974
[36m(train_cnn_ray_tune pid=2697862)[0m Epoch 9/27
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:46[0m 92ms/step - accuracy: 0.1250 - loss: 2.3848
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 41ms/step - accuracy: 0.1736 - loss: 2.2783 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.1792 - loss: 2.2386
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m337/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m12s[0m 50ms/step - accuracy: 0.2758 - loss: 2.1773
[1m339/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 50ms/step - accuracy: 0.2758 - loss: 2.1773[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m345/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 50ms/step - accuracy: 0.2757 - loss: 2.1774[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:14[0m 116ms/step - accuracy: 0.3125 - loss: 2.3537
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 41ms/step - accuracy: 0.3542 - loss: 2.2193  
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 44ms/step - accuracy: 0.1518 - loss: 2.8352
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 44ms/step - accuracy: 0.1518 - loss: 2.8351[32m [repeated 84x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m573/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 42ms/step - accuracy: 0.3003 - loss: 2.1089
[1m575/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.3003 - loss: 2.1088[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.3003 - loss: 2.1088[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 44ms/step - accuracy: 0.1518 - loss: 2.8349[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m369/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 50ms/step - accuracy: 0.2754 - loss: 2.1774
[1m370/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 50ms/step - accuracy: 0.2754 - loss: 2.1774
[1m371/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 50ms/step - accuracy: 0.2754 - loss: 2.1775
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 48ms/step - accuracy: 0.3003 - loss: 2.1088 - val_accuracy: 0.3099 - val_loss: 2.1870
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m36s[0m 44ms/step - accuracy: 0.2342 - loss: 2.3280
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m36s[0m 44ms/step - accuracy: 0.2343 - loss: 2.3279
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m36s[0m 44ms/step - accuracy: 0.2343 - loss: 2.3278
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 30ms/step - accuracy: 0.2564 - loss: 2.2539[32m [repeated 251x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m32s[0m 57ms/step - accuracy: 0.3040 - loss: 2.1128
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m32s[0m 57ms/step - accuracy: 0.3040 - loss: 2.1128[32m [repeated 210x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m50s[0m 43ms/step - accuracy: 0.2390 - loss: 2.3896 - val_accuracy: 0.3020 - val_loss: 2.1805
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 19/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 105ms/step - accuracy: 0.2188 - loss: 1.9313
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m235/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 47ms/step - accuracy: 0.2239 - loss: 2.4547
[1m236/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 47ms/step - accuracy: 0.2239 - loss: 2.4548[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 54/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2895 - loss: 2.0780[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1919 - loss: 2.4860
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1919 - loss: 2.4860
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m25s[0m 33ms/step - accuracy: 0.1920 - loss: 2.4860
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.2208 - loss: 2.3733
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.2208 - loss: 2.3733[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m458/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 49ms/step - accuracy: 0.2748 - loss: 2.1785
[1m459/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 49ms/step - accuracy: 0.2748 - loss: 2.1785[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m451/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 49ms/step - accuracy: 0.2748 - loss: 2.1784[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.3338 - loss: 2.0152[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m57s[0m 49ms/step - accuracy: 0.1519 - loss: 2.8342 - val_accuracy: 0.2063 - val_loss: 2.4231
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:01[0m 105ms/step - accuracy: 0.1250 - loss: 2.8418
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.1319 - loss: 2.7449  
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m26s[0m 56ms/step - accuracy: 0.3030 - loss: 2.1146[32m [repeated 214x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 32ms/step - accuracy: 0.1938 - loss: 2.4864
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m20s[0m 32ms/step - accuracy: 0.1938 - loss: 2.4865[32m [repeated 216x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1597 - loss: 2.2421 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 29ms/step - accuracy: 0.1565 - loss: 2.2856
[36m(train_cnn_ray_tune pid=2697874)[0m Epoch 14/18[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m186/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 37ms/step - accuracy: 0.2978 - loss: 2.0826
[1m188/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 37ms/step - accuracy: 0.2979 - loss: 2.0826[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m359/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.2215 - loss: 2.4655 [32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.2561 - loss: 2.2494
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.2561 - loss: 2.2494
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 29ms/step - accuracy: 0.2561 - loss: 2.2494
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.2519 - loss: 2.2781
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.2520 - loss: 2.2781[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m369/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.2213 - loss: 2.4662
[1m371/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.2213 - loss: 2.4663[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m575/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 48ms/step - accuracy: 0.2746 - loss: 2.1793[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 40ms/step - accuracy: 0.2520 - loss: 2.2780[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:04[0m 108ms/step - accuracy: 0.2500 - loss: 2.2268
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2500 - loss: 2.2725 
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 49ms/step - accuracy: 0.2591 - loss: 2.2828 
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.2647 - loss: 2.2893
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.2677 - loss: 2.2839 
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2560 - loss: 2.2486 
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2560 - loss: 2.2486
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.3339 - loss: 2.0149 - val_accuracy: 0.3603 - val_loss: 2.0224[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43[0m 90ms/step - accuracy: 0.1250 - loss: 2.2643[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 54ms/step - accuracy: 0.2746 - loss: 2.1793 - val_accuracy: 0.3022 - val_loss: 2.2007
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 146/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 41ms/step - accuracy: 0.1551 - loss: 2.7849[32m [repeated 265x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m21s[0m 56ms/step - accuracy: 0.3022 - loss: 2.1161
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m21s[0m 56ms/step - accuracy: 0.3022 - loss: 2.1161[32m [repeated 246x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 29ms/step - accuracy: 0.1493 - loss: 2.2533 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 28ms/step - accuracy: 0.1702 - loss: 2.2434
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 16/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 17/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 49ms/step - accuracy: 0.2691 - loss: 2.1958
[1m 18/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 49ms/step - accuracy: 0.2698 - loss: 2.1957[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m316/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.3008 - loss: 2.0827 [32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.2388 - loss: 2.3154
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.2388 - loss: 2.3154
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m23s[0m 43ms/step - accuracy: 0.2389 - loss: 2.3154
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.2559 - loss: 2.2483
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 29ms/step - accuracy: 0.2559 - loss: 2.2483[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m481/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 45ms/step - accuracy: 0.2197 - loss: 2.4730
[1m482/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 45ms/step - accuracy: 0.2197 - loss: 2.4731[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m477/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 45ms/step - accuracy: 0.2197 - loss: 2.4729[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 53ms/step - accuracy: 0.3280 - loss: 2.0108[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 55/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 48ms/step - accuracy: 0.2820 - loss: 2.1848
[1m 56/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 48ms/step - accuracy: 0.2821 - loss: 2.1847
[1m 57/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 48ms/step - accuracy: 0.2822 - loss: 2.1846
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 54ms/step - accuracy: 0.3281 - loss: 2.0105
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 54ms/step - accuracy: 0.3281 - loss: 2.0105
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 54ms/step - accuracy: 0.3281 - loss: 2.0105
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 31ms/step - accuracy: 0.1949 - loss: 2.4880
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 31ms/step - accuracy: 0.1949 - loss: 2.4880
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 31ms/step - accuracy: 0.1949 - loss: 2.4880
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:24[0m 146ms/step - accuracy: 0.1875 - loss: 2.2718
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1950 - loss: 2.4884 
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1950 - loss: 2.4884
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m15s[0m 55ms/step - accuracy: 0.3016 - loss: 2.1170[32m [repeated 278x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m36s[0m 41ms/step - accuracy: 0.1593 - loss: 2.7752
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m36s[0m 41ms/step - accuracy: 0.1593 - loss: 2.7751[32m [repeated 236x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m118/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m22s[0m 48ms/step - accuracy: 0.2871 - loss: 2.1772
[1m120/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 48ms/step - accuracy: 0.2872 - loss: 2.1770[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m124/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 48ms/step - accuracy: 0.2872 - loss: 2.1767[32m [repeated 23x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 29ms/step - accuracy: 0.2556 - loss: 2.2482
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 29ms/step - accuracy: 0.2556 - loss: 2.2482[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m460/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.3028 - loss: 2.0827
[1m462/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.3028 - loss: 2.0827[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m458/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.3028 - loss: 2.0827[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 29ms/step - accuracy: 0.2556 - loss: 2.2483[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1951 - loss: 2.4888
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1951 - loss: 2.4888
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.1951 - loss: 2.4888[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 51ms/step - accuracy: 0.2187 - loss: 2.4766 - val_accuracy: 0.2704 - val_loss: 2.2683
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 17/28
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:10[0m 121ms/step - accuracy: 0.2500 - loss: 2.3248
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m56s[0m 49ms/step - accuracy: 0.2522 - loss: 2.2776 - val_accuracy: 0.2942 - val_loss: 2.1888
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 33ms/step - accuracy: 0.4097 - loss: 2.1640  
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.2606 - loss: 2.2062
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.2606 - loss: 2.2062
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.2606 - loss: 2.2062
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m30s[0m 40ms/step - accuracy: 0.1595 - loss: 2.7723[32m [repeated 248x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.2409 - loss: 2.3111
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.2410 - loss: 2.3110[32m [repeated 200x across cluster][0m

Trial status: 3 TERMINATED | 17 RUNNING
Current time: 2025-11-07 12:49:22. Total running time: 9min 1s
Logical resource usage: 17.0/20 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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000190495         29                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m232/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 47ms/step - accuracy: 0.2868 - loss: 2.1757
[1m233/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 47ms/step - accuracy: 0.2868 - loss: 2.1757[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 44/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 44ms/step - accuracy: 0.2255 - loss: 2.4033[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 31ms/step - accuracy: 0.1951 - loss: 2.4892
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 31ms/step - accuracy: 0.1951 - loss: 2.4892[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m556/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.3035 - loss: 2.0827
[1m557/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.3035 - loss: 2.0827[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 38ms/step - accuracy: 0.3036 - loss: 2.0826[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 54ms/step - accuracy: 0.3010 - loss: 2.1174[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:23[0m 73ms/step - accuracy: 0.4531 - loss: 1.7290 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:11[0m 62ms/step - accuracy: 0.4340 - loss: 1.7855
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.4271 - loss: 1.8192
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.4192 - loss: 1.8433
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.4231 - loss: 1.8473 
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.4239 - loss: 1.8509
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m268/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 47ms/step - accuracy: 0.2867 - loss: 2.1760
[1m269/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 47ms/step - accuracy: 0.2867 - loss: 2.1760
[1m270/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 47ms/step - accuracy: 0.2867 - loss: 2.1760
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.4191 - loss: 1.8596
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.4170 - loss: 1.8654
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.2396 - loss: 2.3176  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 34ms/step - accuracy: 0.2300 - loss: 2.3008
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.4150 - loss: 1.8713
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 57ms/step - accuracy: 0.4132 - loss: 1.8764
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 58ms/step - accuracy: 0.4118 - loss: 1.8803
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.4100 - loss: 1.8850
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m275/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 47ms/step - accuracy: 0.2867 - loss: 2.1760
[1m276/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 47ms/step - accuracy: 0.2867 - loss: 2.1760
[1m277/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 47ms/step - accuracy: 0.2867 - loss: 2.1760
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.4081 - loss: 1.8898
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 58ms/step - accuracy: 0.4068 - loss: 1.8934
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.4042 - loss: 1.9006
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.4028 - loss: 1.9038
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 56ms/step - accuracy: 0.4016 - loss: 1.9061
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.4005 - loss: 1.9081
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.3995 - loss: 1.9091
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.3985 - loss: 1.9098
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.3977 - loss: 1.9106
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.3967 - loss: 1.9115
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m287/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 48ms/step - accuracy: 0.2866 - loss: 2.1760
[1m288/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 48ms/step - accuracy: 0.2866 - loss: 2.1760
[1m289/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 48ms/step - accuracy: 0.2866 - loss: 2.1760
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  31/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 57ms/step - accuracy: 0.3947 - loss: 1.9135
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  33/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3927 - loss: 1.9160
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  35/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3910 - loss: 1.9178
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 14/24[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  36/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3904 - loss: 1.9185
[1m  37/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3898 - loss: 1.9191
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:06[0m 109ms/step - accuracy: 0.2500 - loss: 2.4608[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  38/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3893 - loss: 1.9195
[1m  39/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3889 - loss: 1.9198
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m37s[0m 32ms/step - accuracy: 0.2555 - loss: 2.2483 - val_accuracy: 0.2940 - val_loss: 2.2070[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  40/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3885 - loss: 1.9201
[1m  41/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3882 - loss: 1.9202
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  43/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 57ms/step - accuracy: 0.3877 - loss: 1.9208
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  44/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3875 - loss: 1.9214
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  45/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3872 - loss: 1.9220
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3870 - loss: 1.9224
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  47/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3867 - loss: 1.9228
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3864 - loss: 1.9231
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3861 - loss: 1.9236
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 57ms/step - accuracy: 0.3856 - loss: 1.9240
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.3852 - loss: 1.9244
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 56ms/step - accuracy: 0.3849 - loss: 1.9249
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m26s[0m 40ms/step - accuracy: 0.1598 - loss: 2.7698
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m26s[0m 40ms/step - accuracy: 0.1598 - loss: 2.7698
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m26s[0m 40ms/step - accuracy: 0.1598 - loss: 2.7697[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3845 - loss: 1.9254
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.3843 - loss: 1.9255
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 27ms/step - accuracy: 0.2210 - loss: 2.3592[32m [repeated 217x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m25s[0m 40ms/step - accuracy: 0.1599 - loss: 2.7692
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m25s[0m 40ms/step - accuracy: 0.1599 - loss: 2.7691[32m [repeated 163x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.3840 - loss: 1.9257
[1m  60/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.3837 - loss: 1.9260
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  62/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3831 - loss: 1.9267
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  63/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 56ms/step - accuracy: 0.3829 - loss: 1.9270
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  65/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3824 - loss: 1.9277
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  67/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3820 - loss: 1.9282
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 47ms/step - accuracy: 0.3036 - loss: 2.0826 - val_accuracy: 0.2998 - val_loss: 2.1999
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  69/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 55ms/step - accuracy: 0.3817 - loss: 1.9285 
[1m  70/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 55ms/step - accuracy: 0.3816 - loss: 1.9287
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:15[0m 131ms/step - accuracy: 0.3750 - loss: 2.1310
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.3750 - loss: 2.0511  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m336/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.2864 - loss: 2.1758
[1m337/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.2864 - loss: 2.1758[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m334/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.2864 - loss: 2.1758[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 55ms/step - accuracy: 0.3008 - loss: 2.1173
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 55ms/step - accuracy: 0.3008 - loss: 2.1173[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m3s[0m 54ms/step - accuracy: 0.3008 - loss: 2.1173[32m [repeated 135x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2422 - loss: 2.3826 
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2422 - loss: 2.3826
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m372/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2863 - loss: 2.1757
[1m373/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2863 - loss: 2.1757
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m375/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2863 - loss: 2.1757
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m377/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2863 - loss: 2.1757
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m378/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1757
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m380/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1757
[1m382/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1757
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m384/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1757
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m386/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1757
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m388/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1757
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m390/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1757
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m391/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1757
[1m392/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1757
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.3056 - loss: 2.3240  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m393/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1757
[1m394/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1756
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m396/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1756
[36m(train_cnn_ray_tune pid=2697856)[0m Epoch 11/29[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m398/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1756
[1m399/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1756
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:07[0m 111ms/step - accuracy: 0.3125 - loss: 2.1638
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m400/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1756
[1m402/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1756
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 42ms/step - accuracy: 0.1787 - loss: 2.6170 - val_accuracy: 0.2561 - val_loss: 2.2887
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m403/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1756
[1m404/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2862 - loss: 2.1756
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m406/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1756
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m407/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1756
[1m408/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1755
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m409/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1755
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m410/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1755
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 27ms/step - accuracy: 0.2201 - loss: 2.3627
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 27ms/step - accuracy: 0.2201 - loss: 2.3628
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 27ms/step - accuracy: 0.2201 - loss: 2.3628
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m412/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1755
[1m413/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1755
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m415/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1755
[1m416/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1755
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m417/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1755
[1m418/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1755
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m420/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1755
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m21s[0m 41ms/step - accuracy: 0.1603 - loss: 2.7668[32m [repeated 208x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.3295 - loss: 1.9945
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.3295 - loss: 1.9945[32m [repeated 173x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m422/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1754
[1m424/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1754
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 36ms/step - accuracy: 0.1953 - loss: 2.4896 - val_accuracy: 0.2406 - val_loss: 2.2726
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:26[0m 75ms/step - accuracy: 0.0625 - loss: 2.5879
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m426/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1754
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.1042 - loss: 2.5125 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.1175 - loss: 2.5500
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m428/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1754
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m430/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1753
[1m432/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1753
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m433/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1753
[1m435/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1753
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m437/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1752
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m258/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 46ms/step - accuracy: 0.2128 - loss: 2.4672
[1m260/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 46ms/step - accuracy: 0.2128 - loss: 2.4674[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m256/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 46ms/step - accuracy: 0.2128 - loss: 2.4671[32m [repeated 70x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m439/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1752
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m441/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1752
[1m443/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1751
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m445/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1751
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m447/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1751
[1m448/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1750
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m449/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1750
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m450/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1750
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m451/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1750
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 27ms/step - accuracy: 0.2199 - loss: 2.3639
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 27ms/step - accuracy: 0.2199 - loss: 2.3640[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m453/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1749
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m455/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1749
[1m456/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1749
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m458/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2861 - loss: 2.1748
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m459/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1748
[1m461/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1748
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 43ms/step - accuracy: 0.2498 - loss: 2.2681[32m [repeated 116x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m463/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1747
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m465/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1747
[1m466/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1747
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m468/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1746
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m470/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1746
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m472/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1745
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m474/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1745
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m476/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1745
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1744
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m479/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1744
[1m481/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1744
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m482/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 48ms/step - accuracy: 0.2860 - loss: 2.1744
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m484/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1743
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m486/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1743
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m488/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1743
[1m490/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1742
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m492/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1742
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m494/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1742
[1m496/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1741
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m498/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1741
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m500/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1741
[1m501/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1740
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m503/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1740
[1m505/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1740
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m507/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1740
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m509/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1739
[1m511/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1739
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 13/26
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m512/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1739
[1m514/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1738
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m516/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1738
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m518/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1738
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m520/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1737
[1m522/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1737
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m524/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1737
[1m525/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1736
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m526/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1736
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m354/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.2122 - loss: 2.4734 
[1m356/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.2121 - loss: 2.4735
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m528/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1736
[1m529/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1736
[1m530/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.2860 - loss: 2.1736
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m27s[0m 48ms/step - accuracy: 0.2690 - loss: 2.2407[32m [repeated 195x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.3312 - loss: 1.9937
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.3312 - loss: 1.9937[32m [repeated 215x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m260/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.3213 - loss: 2.0722
[1m262/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.3213 - loss: 2.0721[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m272/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.3214 - loss: 2.0716[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m54s[0m 47ms/step - accuracy: 0.2421 - loss: 2.3082 - val_accuracy: 0.2990 - val_loss: 2.1210
[36m(train_cnn_ray_tune pid=2697835)[0m Epoch 10/16
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42[0m 89ms/step - accuracy: 0.3125 - loss: 2.0143
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.3403 - loss: 2.1054 
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 42ms/step - accuracy: 0.2635 - loss: 2.2081
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 42ms/step - accuracy: 0.2635 - loss: 2.2081[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 28ms/step - accuracy: 0.2509 - loss: 2.2325
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 28ms/step - accuracy: 0.2509 - loss: 2.2324
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 28ms/step - accuracy: 0.2510 - loss: 2.2324
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 42ms/step - accuracy: 0.2636 - loss: 2.2081[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:51[0m 97ms/step - accuracy: 0.1250 - loss: 2.4287
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.2083 - loss: 2.1864 
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 61ms/step - accuracy: 0.3438 - loss: 2.0075 
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 51ms/step - accuracy: 0.3424 - loss: 2.0735 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.3440 - loss: 2.0774
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m332/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.3216 - loss: 2.0685[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m334/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.3216 - loss: 2.0684
[1m336/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.3216 - loss: 2.0683[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 52ms/step - accuracy: 0.3202 - loss: 2.0791[32m [repeated 216x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 40ms/step - accuracy: 0.1599 - loss: 2.7656
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 40ms/step - accuracy: 0.1599 - loss: 2.7656[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.2859 - loss: 2.1728 - val_accuracy: 0.3047 - val_loss: 2.2074
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 46ms/step - accuracy: 0.2865 - loss: 2.0321  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 52ms/step - accuracy: 0.2969 - loss: 2.0179
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m304/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 37ms/step - accuracy: 0.3215 - loss: 2.0698
[1m306/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.3215 - loss: 2.0697 [32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  6/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 50ms/step - accuracy: 0.3049 - loss: 2.0153[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.2198 - loss: 2.3656 - val_accuracy: 0.2720 - val_loss: 2.2381[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 17/28[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:27[0m 151ms/step - accuracy: 0.3125 - loss: 1.9142[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  17/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 52ms/step - accuracy: 0.3405 - loss: 2.0765 [32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 42ms/step - accuracy: 0.2639 - loss: 2.2080
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 42ms/step - accuracy: 0.2639 - loss: 2.2080[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 30ms/step - accuracy: 0.2037 - loss: 2.4680
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 30ms/step - accuracy: 0.2036 - loss: 2.4681
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m24s[0m 30ms/step - accuracy: 0.2036 - loss: 2.4681[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 42ms/step - accuracy: 0.2640 - loss: 2.2080[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:54[0m 99ms/step - accuracy: 0.1875 - loss: 2.1631
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.2031 - loss: 2.1955 
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.2049 - loss: 2.3835 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.2117 - loss: 2.4059
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m531/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 45ms/step - accuracy: 0.2124 - loss: 2.4787[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m460/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.3211 - loss: 2.0665
[1m462/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 38ms/step - accuracy: 0.3211 - loss: 2.0665[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2546 - loss: 2.2317 
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2546 - loss: 2.2317
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m24s[0m 35ms/step - accuracy: 0.1809 - loss: 2.6330[32m [repeated 307x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 55ms/step - accuracy: 0.3068 - loss: 2.1036
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 55ms/step - accuracy: 0.3067 - loss: 2.1036[32m [repeated 224x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m102/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 52ms/step - accuracy: 0.2997 - loss: 2.1048
[1m104/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 52ms/step - accuracy: 0.2996 - loss: 2.1054[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m101/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m24s[0m 52ms/step - accuracy: 0.2998 - loss: 2.1045[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 40ms/step - accuracy: 0.2417 - loss: 2.3795 - val_accuracy: 0.3038 - val_loss: 2.1664
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 11/27
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 41ms/step - accuracy: 0.1599 - loss: 2.7655
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 41ms/step - accuracy: 0.1599 - loss: 2.7655[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m35s[0m 51ms/step - accuracy: 0.3543 - loss: 1.9618
[1m 470/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m35s[0m 51ms/step - accuracy: 0.3543 - loss: 1.9618
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m34s[0m 51ms/step - accuracy: 0.3543 - loss: 1.9618[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 35ms/step - accuracy: 0.3339 - loss: 1.9909[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.3201 - loss: 2.0664[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m573/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.3201 - loss: 2.0664
[1m575/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.3201 - loss: 2.0664[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 52ms/step - accuracy: 0.2126 - loss: 2.4795 - val_accuracy: 0.2644 - val_loss: 2.2704
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 18/28
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 110ms/step - accuracy: 0.2812 - loss: 2.3499
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2569 - loss: 2.2840  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2442 - loss: 2.3052
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m50s[0m 54ms/step - accuracy: 0.3038 - loss: 2.1073[32m [repeated 279x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m37s[0m 43ms/step - accuracy: 0.2658 - loss: 2.2098
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m37s[0m 43ms/step - accuracy: 0.2658 - loss: 2.2099[32m [repeated 205x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m55s[0m 48ms/step - accuracy: 0.2641 - loss: 2.2080 - val_accuracy: 0.3395 - val_loss: 2.0893
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.3750 - loss: 2.0354  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.3450 - loss: 2.0807
Trial status: 3 TERMINATED | 17 RUNNING
Current time: 2025-11-07 12:49:52. Total running time: 9min 31s
Logical resource usage: 17.0/20 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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000190495         29                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m203/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 50ms/step - accuracy: 0.2974 - loss: 2.1200
[1m205/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 50ms/step - accuracy: 0.2973 - loss: 2.1202[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 42/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 47ms/step - accuracy: 0.2131 - loss: 2.4479[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 28ms/step - accuracy: 0.2556 - loss: 2.2317
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 28ms/step - accuracy: 0.2556 - loss: 2.2317[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.1811 - loss: 2.6271
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.1812 - loss: 2.6270
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.1812 - loss: 2.6270[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 28ms/step - accuracy: 0.2556 - loss: 2.2316[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 44ms/step - accuracy: 0.3201 - loss: 2.0664 - val_accuracy: 0.3065 - val_loss: 2.1854
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 21/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:33[0m 81ms/step - accuracy: 0.3125 - loss: 1.8888[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 45ms/step - accuracy: 0.3681 - loss: 1.8506 
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 28ms/step - accuracy: 0.2560 - loss: 2.2312
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 28ms/step - accuracy: 0.2560 - loss: 2.2312
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 28ms/step - accuracy: 0.2560 - loss: 2.2312
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2778 - loss: 2.0955  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.3064 - loss: 2.0671
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m284/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 51ms/step - accuracy: 0.2954 - loss: 2.1262
[1m285/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 51ms/step - accuracy: 0.2954 - loss: 2.1263
[1m286/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 51ms/step - accuracy: 0.2954 - loss: 2.1263
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m31s[0m 43ms/step - accuracy: 0.2654 - loss: 2.2144[32m [repeated 295x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m45s[0m 54ms/step - accuracy: 0.3036 - loss: 2.1064
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m44s[0m 54ms/step - accuracy: 0.3036 - loss: 2.1063[32m [repeated 222x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m46s[0m 40ms/step - accuracy: 0.3341 - loss: 1.9907 - val_accuracy: 0.3411 - val_loss: 2.0441
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m301/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 51ms/step - accuracy: 0.2951 - loss: 2.1272
[1m302/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 51ms/step - accuracy: 0.2950 - loss: 2.1272[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m119/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 41ms/step - accuracy: 0.3255 - loss: 2.0363[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2687 - loss: 2.2507
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2687 - loss: 2.2507[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.2686 - loss: 2.2508[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.3516 - loss: 1.9656
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.3516 - loss: 1.9656
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.3516 - loss: 1.9656
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m54s[0m 46ms/step - accuracy: 0.1600 - loss: 2.7652 - val_accuracy: 0.2124 - val_loss: 2.4031
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 37ms/step - accuracy: 0.0938 - loss: 2.8844  
[36m(train_cnn_ray_tune pid=2697871)[0m Epoch 10/17[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:16[0m 118ms/step - accuracy: 0.0625 - loss: 2.9676
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1994 - loss: 2.4735
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1994 - loss: 2.4735
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.1994 - loss: 2.4735
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m383/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2939 - loss: 2.1308 
[1m384/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2939 - loss: 2.1308
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m40s[0m 55ms/step - accuracy: 0.3037 - loss: 2.1059[32m [repeated 286x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.1808 - loss: 2.6190
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.1808 - loss: 2.6190[32m [repeated 196x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m385/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2939 - loss: 2.1308
[1m386/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2939 - loss: 2.1309
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:27[0m 128ms/step - accuracy: 0.2500 - loss: 2.0901
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.2812 - loss: 2.0736  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m387/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2939 - loss: 2.1309
[1m388/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2939 - loss: 2.1309
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m390/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2939 - loss: 2.1310
[1m392/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2938 - loss: 2.1311
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m394/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2938 - loss: 2.1312
[1m395/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2938 - loss: 2.1312
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1807 - loss: 2.6186 
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.1807 - loss: 2.6186
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m397/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2938 - loss: 2.1313
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m398/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2938 - loss: 2.1313
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m232/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 42ms/step - accuracy: 0.3216 - loss: 2.0401
[1m233/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 42ms/step - accuracy: 0.3216 - loss: 2.0401[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m248/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m15s[0m 48ms/step - accuracy: 0.2132 - loss: 2.4626[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m236/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 42ms/step - accuracy: 0.3215 - loss: 2.0402
[1m237/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 42ms/step - accuracy: 0.3215 - loss: 2.0402
[1m238/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m14s[0m 42ms/step - accuracy: 0.3215 - loss: 2.0403
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m400/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2937 - loss: 2.1314
[1m402/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.2937 - loss: 2.1315
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m403/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2937 - loss: 2.1315
[1m404/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2937 - loss: 2.1315
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m405/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2937 - loss: 2.1316
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m407/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2937 - loss: 2.1317
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m408/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2937 - loss: 2.1317
[1m409/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2936 - loss: 2.1317
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 31ms/step - accuracy: 0.1992 - loss: 2.4739
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 31ms/step - accuracy: 0.1992 - loss: 2.4739[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m411/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2936 - loss: 2.1318
[1m412/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2936 - loss: 2.1319
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m414/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2936 - loss: 2.1319
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m416/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2935 - loss: 2.1320
[1m417/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2935 - loss: 2.1321
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m418/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2935 - loss: 2.1321
[1m419/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2935 - loss: 2.1322
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m420/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2935 - loss: 2.1322
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 37ms/step - accuracy: 0.1807 - loss: 2.6180[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m421/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2935 - loss: 2.1322
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m422/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 51ms/step - accuracy: 0.2935 - loss: 2.1323
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m423/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2934 - loss: 2.1323
[1m424/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2934 - loss: 2.1324
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m26s[0m 44ms/step - accuracy: 0.2645 - loss: 2.2182
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m26s[0m 44ms/step - accuracy: 0.2645 - loss: 2.2182
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m26s[0m 44ms/step - accuracy: 0.2645 - loss: 2.2182[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m426/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2934 - loss: 2.1324
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m428/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2934 - loss: 2.1325
[1m430/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2934 - loss: 2.1326
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 33ms/step - accuracy: 0.2561 - loss: 2.2310 - val_accuracy: 0.2946 - val_loss: 2.1795
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m431/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2933 - loss: 2.1326
[1m432/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2933 - loss: 2.1327
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m434/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2933 - loss: 2.1328
[1m435/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2933 - loss: 2.1328
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m437/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2933 - loss: 2.1329
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m439/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2932 - loss: 2.1330
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m441/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 51ms/step - accuracy: 0.2932 - loss: 2.1331
[1m443/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2932 - loss: 2.1331
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m444/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2932 - loss: 2.1332
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m446/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2931 - loss: 2.1332
[1m447/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2931 - loss: 2.1333
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m449/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2931 - loss: 2.1334
[1m451/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2931 - loss: 2.1334
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m453/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2931 - loss: 2.1335
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m455/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2930 - loss: 2.1336
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 15/24
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m457/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2930 - loss: 2.1336
[1m458/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2930 - loss: 2.1337
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m459/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2930 - loss: 2.1337
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m460/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 51ms/step - accuracy: 0.2930 - loss: 2.1338
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m461/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2930 - loss: 2.1338
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m462/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2930 - loss: 2.1338
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m464/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2929 - loss: 2.1339
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m466/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2929 - loss: 2.1340
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m468/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2929 - loss: 2.1340
[1m470/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2929 - loss: 2.1341
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m472/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2929 - loss: 2.1342
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m474/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2928 - loss: 2.1343
[1m475/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2928 - loss: 2.1343
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m476/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2928 - loss: 2.1343
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2928 - loss: 2.1344
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m479/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 51ms/step - accuracy: 0.2928 - loss: 2.1345
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m481/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 51ms/step - accuracy: 0.2928 - loss: 2.1345
[1m482/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 51ms/step - accuracy: 0.2927 - loss: 2.1346
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m35s[0m 55ms/step - accuracy: 0.3036 - loss: 2.1058[32m [repeated 271x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 30ms/step - accuracy: 0.2563 - loss: 2.1879
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 29ms/step - accuracy: 0.2563 - loss: 2.1882[32m [repeated 201x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m483/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 51ms/step - accuracy: 0.2927 - loss: 2.1346
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m485/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 51ms/step - accuracy: 0.2927 - loss: 2.1347
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m487/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 51ms/step - accuracy: 0.2927 - loss: 2.1347
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m342/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.3200 - loss: 2.0422 
[1m344/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.3200 - loss: 2.0422
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m489/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 51ms/step - accuracy: 0.2927 - loss: 2.1348
[1m490/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 51ms/step - accuracy: 0.2927 - loss: 2.1348
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2186 - loss: 2.3709 
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2186 - loss: 2.3708
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m353/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.3200 - loss: 2.0424
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m357/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 47ms/step - accuracy: 0.2124 - loss: 2.4685
[1m359/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 47ms/step - accuracy: 0.2124 - loss: 2.4686[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m361/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 47ms/step - accuracy: 0.2124 - loss: 2.4686[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.1985 - loss: 2.4746
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 32ms/step - accuracy: 0.1985 - loss: 2.4746[32m [repeated 91x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 37ms/step - accuracy: 0.1807 - loss: 2.6151[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 44ms/step - accuracy: 0.2680 - loss: 2.2514 - val_accuracy: 0.2867 - val_loss: 2.2049
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 11/27
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:55[0m 100ms/step - accuracy: 0.3125 - loss: 2.2758
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.3646 - loss: 2.2210  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.3556 - loss: 2.1774
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m29s[0m 54ms/step - accuracy: 0.3040 - loss: 2.1044[32m [repeated 252x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 28ms/step - accuracy: 0.2589 - loss: 2.1970
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 28ms/step - accuracy: 0.2589 - loss: 2.1971[32m [repeated 196x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m463/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 47ms/step - accuracy: 0.2125 - loss: 2.4709
[1m465/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 46ms/step - accuracy: 0.2125 - loss: 2.4709[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m483/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 41ms/step - accuracy: 0.3198 - loss: 2.0439[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m367/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 47ms/step - accuracy: 0.2124 - loss: 2.4688
[1m369/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 47ms/step - accuracy: 0.2124 - loss: 2.4689 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.3500 - loss: 1.9667
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 51ms/step - accuracy: 0.3500 - loss: 1.9667[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1319 - loss: 2.4361     
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1542 - loss: 2.4967
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m8s[0m 51ms/step - accuracy: 0.3500 - loss: 1.9667[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.2884 - loss: 2.2495 
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.2914 - loss: 2.2393
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 56ms/step - accuracy: 0.2919 - loss: 2.1373 - val_accuracy: 0.3004 - val_loss: 2.2025
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 52ms/step - accuracy: 0.3229 - loss: 2.1088  
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 52ms/step - accuracy: 0.3145 - loss: 2.1171
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  6/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 44ms/step - accuracy: 0.3204 - loss: 2.1003
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  8/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 43ms/step - accuracy: 0.3264 - loss: 2.0884
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 482/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 28ms/step - accuracy: 0.2598 - loss: 2.2004
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 28ms/step - accuracy: 0.2598 - loss: 2.2004
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 28ms/step - accuracy: 0.2598 - loss: 2.2004
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 19/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 44ms/step - accuracy: 0.3189 - loss: 2.0898
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 21/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.3170 - loss: 2.0919
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 23/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.3148 - loss: 2.0943
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 25/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.3124 - loss: 2.0966
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 26/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 45ms/step - accuracy: 0.3113 - loss: 2.0976
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 30/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 46ms/step - accuracy: 0.3074 - loss: 2.1016
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.2561 - loss: 2.2670 
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.2561 - loss: 2.2670
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 36/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 46ms/step - accuracy: 0.3021 - loss: 2.1076
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 37/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 46ms/step - accuracy: 0.3015 - loss: 2.1085
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m65s[0m 56ms/step - accuracy: 0.2669 - loss: 2.2411 - val_accuracy: 0.2877 - val_loss: 2.1966[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 18/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 39/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 47ms/step - accuracy: 0.3003 - loss: 2.1097
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 113ms/step - accuracy: 0.3438 - loss: 2.1334[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 40/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 47ms/step - accuracy: 0.2998 - loss: 2.1102
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 41ms/step - accuracy: 0.2674 - loss: 2.3365  
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 49ms/step - accuracy: 0.2708 - loss: 2.3109
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m24s[0m 54ms/step - accuracy: 0.3041 - loss: 2.1030[32m [repeated 316x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 32ms/step - accuracy: 0.2014 - loss: 2.4741
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 32ms/step - accuracy: 0.2013 - loss: 2.4739[32m [repeated 203x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 48/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.2967 - loss: 2.1135
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m573/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 46ms/step - accuracy: 0.2130 - loss: 2.4718
[1m574/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 46ms/step - accuracy: 0.2130 - loss: 2.4718[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 58/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.2938 - loss: 2.1171
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 60/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.2934 - loss: 2.1176
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 46ms/step - accuracy: 0.2130 - loss: 2.4718[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 62/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.2929 - loss: 2.1181
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 63/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.2927 - loss: 2.1184
[1m 64/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 47ms/step - accuracy: 0.2925 - loss: 2.1186[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 51ms/step - accuracy: 0.1719 - loss: 2.6176  
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.1523 - loss: 2.6336
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 78ms/step - accuracy: 0.1250 - loss: 2.7427
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2153 - loss: 2.5013 
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 51ms/step - accuracy: 0.3498 - loss: 1.9668
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 51ms/step - accuracy: 0.3498 - loss: 1.9668[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 85/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 47ms/step - accuracy: 0.2893 - loss: 2.1213
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 42ms/step - accuracy: 0.2563 - loss: 2.2665[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 87/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 47ms/step - accuracy: 0.2891 - loss: 2.1215
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 52ms/step - accuracy: 0.3498 - loss: 1.9668
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 52ms/step - accuracy: 0.3498 - loss: 1.9668
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 52ms/step - accuracy: 0.3498 - loss: 1.9668
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 91/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 48ms/step - accuracy: 0.2888 - loss: 2.1219
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 93/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 48ms/step - accuracy: 0.2887 - loss: 2.1220
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 97/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 48ms/step - accuracy: 0.2884 - loss: 2.1224
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 46ms/step - accuracy: 0.3196 - loss: 2.0450 - val_accuracy: 0.3218 - val_loss: 2.1644
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m109/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 48ms/step - accuracy: 0.2874 - loss: 2.1241[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.2130 - loss: 2.4718 - val_accuracy: 0.2672 - val_loss: 2.2579
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.2637 - loss: 2.2215 
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 43ms/step - accuracy: 0.2637 - loss: 2.2215[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m29s[0m 33ms/step - accuracy: 0.2010 - loss: 2.4589
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m29s[0m 33ms/step - accuracy: 0.2010 - loss: 2.4587
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m29s[0m 33ms/step - accuracy: 0.2010 - loss: 2.4585
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m37s[0m 32ms/step - accuracy: 0.2195 - loss: 2.3677 - val_accuracy: 0.2750 - val_loss: 2.2362[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 19/28[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 121ms/step - accuracy: 0.0938 - loss: 2.7168[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 257/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m36s[0m 40ms/step - accuracy: 0.2807 - loss: 2.1798[32m [repeated 282x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m19s[0m 54ms/step - accuracy: 0.3045 - loss: 2.1015
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m19s[0m 54ms/step - accuracy: 0.3045 - loss: 2.1015[32m [repeated 210x across cluster][0m
Trial status: 3 TERMINATED | 17 RUNNING
Current time: 2025-11-07 12:50:22. Total running time: 10min 1s
Logical resource usage: 17.0/20 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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000190495         29                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 31/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 51ms/step - accuracy: 0.1946 - loss: 2.4664
[1m 33/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 50ms/step - accuracy: 0.1957 - loss: 2.4655[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 52ms/step - accuracy: 0.3495 - loss: 1.9670
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 52ms/step - accuracy: 0.3495 - loss: 1.9670
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 52ms/step - accuracy: 0.3495 - loss: 1.9670
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 44ms/step - accuracy: 0.2637 - loss: 2.2216
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 44ms/step - accuracy: 0.2637 - loss: 2.2216[32m [repeated 79x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 44ms/step - accuracy: 0.2638 - loss: 2.2216[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 80/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 48ms/step - accuracy: 0.2022 - loss: 2.4745[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2606 - loss: 2.2051 
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2606 - loss: 2.2052
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m25s[0m 28ms/step - accuracy: 0.2360 - loss: 2.3230
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m25s[0m 28ms/step - accuracy: 0.2359 - loss: 2.3232
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m25s[0m 28ms/step - accuracy: 0.2358 - loss: 2.3233
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m21s[0m 42ms/step - accuracy: 0.1601 - loss: 2.7700
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m21s[0m 42ms/step - accuracy: 0.1601 - loss: 2.7699
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m21s[0m 42ms/step - accuracy: 0.1601 - loss: 2.7699
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m30s[0m 39ms/step - accuracy: 0.2776 - loss: 2.1907[32m [repeated 254x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 54ms/step - accuracy: 0.3048 - loss: 2.1000
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m14s[0m 54ms/step - accuracy: 0.3048 - loss: 2.1000[32m [repeated 218x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m148/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 45ms/step - accuracy: 0.2052 - loss: 2.4832
[1m149/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 46ms/step - accuracy: 0.2053 - loss: 2.4833[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.2609 - loss: 2.2065
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.2609 - loss: 2.2065[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.2609 - loss: 2.2066[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m199/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m16s[0m 44ms/step - accuracy: 0.2067 - loss: 2.4839[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m68s[0m 58ms/step - accuracy: 0.3495 - loss: 1.9670 - val_accuracy: 0.3200 - val_loss: 2.1114
[36m(train_cnn_ray_tune pid=2697863)[0m Epoch 9/29
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:06[0m 110ms/step - accuracy: 0.2500 - loss: 2.0561
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.3507 - loss: 1.9140  
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 27ms/step - accuracy: 0.2298 - loss: 2.3337
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 27ms/step - accuracy: 0.2297 - loss: 2.3338
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m18s[0m 27ms/step - accuracy: 0.2297 - loss: 2.3339
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m320/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3177 - loss: 2.0301 
[1m322/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3177 - loss: 2.0301
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.3140 - loss: 2.0450 
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 27ms/step - accuracy: 0.2281 - loss: 2.3368[32m [repeated 221x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 42ms/step - accuracy: 0.1614 - loss: 2.7661
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m15s[0m 42ms/step - accuracy: 0.1614 - loss: 2.7660[32m [repeated 181x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m324/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3177 - loss: 2.0302
[1m326/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3177 - loss: 2.0302
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m328/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3177 - loss: 2.0303
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m330/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3177 - loss: 2.0303
[1m332/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3177 - loss: 2.0304
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2500 - loss: 2.0374 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:12[0m 63ms/step - accuracy: 0.2431 - loss: 2.0844
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m264/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.2083 - loss: 2.4833
[1m265/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.2083 - loss: 2.4833[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m394/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 47ms/step - accuracy: 0.2848 - loss: 2.1426
[1m395/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 47ms/step - accuracy: 0.2848 - loss: 2.1426
[1m396/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 48ms/step - accuracy: 0.2848 - loss: 2.1426
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 44ms/step - accuracy: 0.2768 - loss: 2.1949
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 44ms/step - accuracy: 0.2767 - loss: 2.1949[32m [repeated 67x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m406/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 47ms/step - accuracy: 0.2849 - loss: 2.1426
[1m407/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 47ms/step - accuracy: 0.2849 - loss: 2.1426
[1m408/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 47ms/step - accuracy: 0.2849 - loss: 2.1426
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 44ms/step - accuracy: 0.2767 - loss: 2.1948[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 27ms/step - accuracy: 0.2268 - loss: 2.3390
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 27ms/step - accuracy: 0.2268 - loss: 2.3391
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 27ms/step - accuracy: 0.2268 - loss: 2.3391
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m314/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m11s[0m 44ms/step - accuracy: 0.2096 - loss: 2.4830[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m429/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.2851 - loss: 2.1426
[1m431/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 47ms/step - accuracy: 0.2851 - loss: 2.1426
[1m432/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 47ms/step - accuracy: 0.2851 - loss: 2.1426
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m56s[0m 49ms/step - accuracy: 0.2638 - loss: 2.2216 - val_accuracy: 0.2968 - val_loss: 2.1849[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m Epoch 11/25[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:13[0m 116ms/step - accuracy: 0.4375 - loss: 2.0367[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.2257 - loss: 2.1721 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m19s[0m 39ms/step - accuracy: 0.2755 - loss: 2.2029[32m [repeated 285x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 44ms/step - accuracy: 0.2501 - loss: 2.2258
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 44ms/step - accuracy: 0.2501 - loss: 2.2259[32m [repeated 185x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m470/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 47ms/step - accuracy: 0.2854 - loss: 2.1426
[1m472/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 47ms/step - accuracy: 0.2854 - loss: 2.1426[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m356/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.2107 - loss: 2.4821 
[1m358/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.2107 - loss: 2.4820
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m474/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 47ms/step - accuracy: 0.2854 - loss: 2.1426[32m [repeated 66x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.4219 - loss: 2.0692 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.3750 - loss: 2.1343 
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1624 - loss: 2.7627 
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 42ms/step - accuracy: 0.1624 - loss: 2.7626
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m350/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 45ms/step - accuracy: 0.2105 - loss: 2.4823
[1m351/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 45ms/step - accuracy: 0.2106 - loss: 2.4822[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 54ms/step - accuracy: 0.3052 - loss: 2.0972
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 54ms/step - accuracy: 0.3052 - loss: 2.0972[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 42ms/step - accuracy: 0.1626 - loss: 2.7619[32m [repeated 105x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:04[0m 108ms/step - accuracy: 0.1875 - loss: 2.4248
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.2326 - loss: 2.3846  
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m354/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 45ms/step - accuracy: 0.2106 - loss: 2.4821[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 32ms/step - accuracy: 0.2615 - loss: 2.2077 - val_accuracy: 0.3043 - val_loss: 2.1831
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 16/24
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 44ms/step - accuracy: 0.2766 - loss: 2.1940
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 44ms/step - accuracy: 0.2766 - loss: 2.1940
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 44ms/step - accuracy: 0.2766 - loss: 2.1940
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m  74/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 31ms/step - accuracy: 0.2642 - loss: 2.1949
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 31ms/step - accuracy: 0.2644 - loss: 2.1940
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 31ms/step - accuracy: 0.2646 - loss: 2.1929
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m14s[0m 39ms/step - accuracy: 0.2748 - loss: 2.2071[32m [repeated 256x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 31ms/step - accuracy: 0.2649 - loss: 2.1917
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 30ms/step - accuracy: 0.2654 - loss: 2.1901[32m [repeated 175x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m463/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 45ms/step - accuracy: 0.2125 - loss: 2.4790
[1m464/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 45ms/step - accuracy: 0.2125 - loss: 2.4790[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m468/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 45ms/step - accuracy: 0.2126 - loss: 2.4789[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.2009 - loss: 2.4509 
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.2009 - loss: 2.4509
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.3602 - loss: 1.9410 - val_accuracy: 0.3389 - val_loss: 2.0298
[36m(train_cnn_ray_tune pid=2697873)[0m Epoch 13/28
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 42ms/step - accuracy: 0.1631 - loss: 2.7594
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 42ms/step - accuracy: 0.1631 - loss: 2.7593[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2009 - loss: 2.4513[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45[0m 91ms/step - accuracy: 0.3750 - loss: 2.2018
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 39ms/step - accuracy: 0.4167 - loss: 2.0213 
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.2858 - loss: 2.1424 - val_accuracy: 0.3256 - val_loss: 2.1818
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 93ms/step - accuracy: 0.1875 - loss: 2.2199
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.2257 - loss: 2.2135
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2415 - loss: 2.1939
[1m  6/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 40ms/step - accuracy: 0.2647 - loss: 2.1669
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  8/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 40ms/step - accuracy: 0.2763 - loss: 2.1470
[1m 10/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2829 - loss: 2.1379
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 12/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2856 - loss: 2.1336
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 14/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2876 - loss: 2.1328
[1m 16/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.2892 - loss: 2.1340
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 18/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.2908 - loss: 2.1348
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 20/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.2927 - loss: 2.1344
[1m 22/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.2944 - loss: 2.1325
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 24/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.2956 - loss: 2.1313
[1m 26/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2965 - loss: 2.1312
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 28/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2968 - loss: 2.1323
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 30/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2971 - loss: 2.1334
[1m 32/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2970 - loss: 2.1347
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m44s[0m 50ms/step - accuracy: 0.3456 - loss: 1.9525
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m44s[0m 50ms/step - accuracy: 0.3456 - loss: 1.9525
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m44s[0m 50ms/step - accuracy: 0.3456 - loss: 1.9525
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 34/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2967 - loss: 2.1364
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 36/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2964 - loss: 2.1379
[1m 38/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2964 - loss: 2.1386
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m26s[0m 35ms/step - accuracy: 0.2476 - loss: 2.3160[32m [repeated 180x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 30ms/step - accuracy: 0.3689 - loss: 1.9077
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 30ms/step - accuracy: 0.3689 - loss: 1.9075[32m [repeated 224x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m576/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 44ms/step - accuracy: 0.2139 - loss: 2.4761
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 44ms/step - accuracy: 0.2139 - loss: 2.4760[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 40/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2964 - loss: 2.1392
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m574/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 44ms/step - accuracy: 0.2138 - loss: 2.4761[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 42/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2962 - loss: 2.1399
[1m 44/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2960 - loss: 2.1404
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 46/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2958 - loss: 2.1410
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 119ms/step - accuracy: 0.2500 - loss: 2.1374
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 48/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2957 - loss: 2.1414
[1m 50/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2957 - loss: 2.1416
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 35ms/step - accuracy: 0.2587 - loss: 2.1224  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.2708 - loss: 2.1088
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 52/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 38ms/step - accuracy: 0.2958 - loss: 2.1417
[1m 54/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 38ms/step - accuracy: 0.2958 - loss: 2.1420
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 39ms/step - accuracy: 0.3507 - loss: 1.9362  
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m56s[0m 48ms/step - accuracy: 0.2766 - loss: 2.1939 - val_accuracy: 0.3375 - val_loss: 2.0830
[36m(train_cnn_ray_tune pid=2697862)[0m Epoch 11/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 31ms/step - accuracy: 0.2009 - loss: 2.4519
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 31ms/step - accuracy: 0.2009 - loss: 2.4520[32m [repeated 93x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m70s[0m 60ms/step - accuracy: 0.3053 - loss: 2.0965 - val_accuracy: 0.3570 - val_loss: 2.0399
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 59ms/step - accuracy: 0.2847 - loss: 2.2349
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:08[0m 60ms/step - accuracy: 0.2878 - loss: 2.1997
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 38ms/step - accuracy: 0.2743 - loss: 2.2114[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.2977 - loss: 2.1342
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.3067 - loss: 2.0976
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 53ms/step - accuracy: 0.3097 - loss: 2.0886
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.3157 - loss: 2.0679 
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.3232 - loss: 2.0428 
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.3293 - loss: 2.0226
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.3304 - loss: 2.0206
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.3321 - loss: 2.0196
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.3327 - loss: 2.0192
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3336 - loss: 2.0189
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3343 - loss: 2.0188
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3351 - loss: 2.0184
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.3357 - loss: 2.0179
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3362 - loss: 2.0179
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.3369 - loss: 2.0178
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  31/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.3373 - loss: 2.0178
[1m  32/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3376 - loss: 2.0182
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 50ms/step - accuracy: 0.2139 - loss: 2.4760 - val_accuracy: 0.2712 - val_loss: 2.2560[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  33/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3378 - loss: 2.0189
[1m  34/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3379 - loss: 2.0195
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 114ms/step - accuracy: 0.2188 - loss: 2.4986
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 32ms/step - accuracy: 0.2066 - loss: 2.4972  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  35/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3380 - loss: 2.0200
[1m  36/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3380 - loss: 2.0207
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 85/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 38ms/step - accuracy: 0.3245 - loss: 2.0326
[1m 87/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m18s[0m 38ms/step - accuracy: 0.3245 - loss: 2.0325[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  37/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3382 - loss: 2.0211
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  38/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 56ms/step - accuracy: 0.3384 - loss: 2.0216
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  40/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.3389 - loss: 2.0226
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 94/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m18s[0m 38ms/step - accuracy: 0.3245 - loss: 2.0326[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  42/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.3394 - loss: 2.0238
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  43/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.3395 - loss: 2.0246
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  45/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3396 - loss: 2.0263
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.3396 - loss: 2.0271
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  47/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.3396 - loss: 2.0279
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.3396 - loss: 2.0289
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 55ms/step - accuracy: 0.3395 - loss: 2.0299
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3393 - loss: 2.0315
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3391 - loss: 2.0329
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3387 - loss: 2.0344
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3384 - loss: 2.0359
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3382 - loss: 2.0368
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3379 - loss: 2.0377
[1m  60/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 55ms/step - accuracy: 0.3377 - loss: 2.0385
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m34s[0m 49ms/step - accuracy: 0.3480 - loss: 1.9503[32m [repeated 205x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 26ms/step - accuracy: 0.2746 - loss: 2.1736
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m17s[0m 26ms/step - accuracy: 0.2745 - loss: 2.1737[32m [repeated 198x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  62/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 55ms/step - accuracy: 0.3373 - loss: 2.0400 
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.1800 - loss: 2.5804
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.1800 - loss: 2.5804
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.1800 - loss: 2.5804
Trial status: 3 TERMINATED | 17 RUNNING
Current time: 2025-11-07 12:50:52. Total running time: 10min 31s
Logical resource usage: 17.0/20 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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000190495         29                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:07[0m 110ms/step - accuracy: 0.4375 - loss: 1.6992
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:59[0m 103ms/step - accuracy: 0.0625 - loss: 2.6804
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.0625 - loss: 2.6608 
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.2153 - loss: 2.6047  
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.0885 - loss: 2.6344 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 46ms/step - accuracy: 0.1007 - loss: 2.6427
[36m(train_cnn_ray_tune pid=2697874)[0m Epoch 17/18[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1801 - loss: 2.5802
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 36ms/step - accuracy: 0.1801 - loss: 2.5802[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.2256 - loss: 2.3406 - val_accuracy: 0.2720 - val_loss: 2.2179[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 38ms/step - accuracy: 0.2740 - loss: 2.2133[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m212/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 45ms/step - accuracy: 0.2925 - loss: 2.1378
[1m213/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 45ms/step - accuracy: 0.2925 - loss: 2.1378
[1m214/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 45ms/step - accuracy: 0.2925 - loss: 2.1378
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:14[0m 116ms/step - accuracy: 0.2500 - loss: 2.4239
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.2292 - loss: 2.4279  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m226/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m15s[0m 45ms/step - accuracy: 0.2924 - loss: 2.1375
[1m227/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m15s[0m 45ms/step - accuracy: 0.2924 - loss: 2.1375[32m [repeated 45x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m228/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m15s[0m 45ms/step - accuracy: 0.2924 - loss: 2.1375[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 29ms/step - accuracy: 0.2374 - loss: 2.3360
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 29ms/step - accuracy: 0.2373 - loss: 2.3361
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 29ms/step - accuracy: 0.2371 - loss: 2.3362
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 148/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 57ms/step - accuracy: 0.3282 - loss: 2.0560[32m [repeated 340x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 100/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 43ms/step - accuracy: 0.1762 - loss: 2.6719
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 43ms/step - accuracy: 0.1762 - loss: 2.6727[32m [repeated 218x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:12[0m 114ms/step - accuracy: 0.1250 - loss: 2.9710
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 15/26
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 36ms/step - accuracy: 0.1806 - loss: 2.5793
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 36ms/step - accuracy: 0.1806 - loss: 2.5793[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 36ms/step - accuracy: 0.2009 - loss: 2.4520 - val_accuracy: 0.2607 - val_loss: 2.2583
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.1806 - loss: 2.5792[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m324/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3218 - loss: 2.0356 
[1m326/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3218 - loss: 2.0356
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m328/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3218 - loss: 2.0356
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m330/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3218 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m332/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3219 - loss: 2.0355
[1m334/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3219 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m336/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3219 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m338/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3219 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m340/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3219 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m342/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3219 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m227/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 48ms/step - accuracy: 0.2199 - loss: 2.4227
[1m229/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m16s[0m 48ms/step - accuracy: 0.2198 - loss: 2.4229[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m344/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3220 - loss: 2.0355
[1m346/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3220 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m234/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m16s[0m 48ms/step - accuracy: 0.2198 - loss: 2.4234[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m348/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3220 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m350/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3220 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m352/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3220 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m354/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3220 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m356/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3221 - loss: 2.0355
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m358/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3221 - loss: 2.0354
[1m360/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3221 - loss: 2.0354
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m50s[0m 43ms/step - accuracy: 0.2740 - loss: 2.2137 - val_accuracy: 0.2994 - val_loss: 2.1964
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 12/27
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m362/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3221 - loss: 2.0354
[1m363/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3221 - loss: 2.0354
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:11[0m 114ms/step - accuracy: 0.1250 - loss: 2.2191
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m365/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3221 - loss: 2.0354
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 43ms/step - accuracy: 0.1736 - loss: 2.2493  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 44ms/step - accuracy: 0.1992 - loss: 2.2302
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m367/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3221 - loss: 2.0354
[1m369/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3222 - loss: 2.0354
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m371/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3222 - loss: 2.0354
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m372/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3222 - loss: 2.0354
[1m374/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3222 - loss: 2.0354
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m376/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3222 - loss: 2.0354
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m378/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3222 - loss: 2.0354
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.3696 - loss: 1.9024[32m [repeated 251x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m51s[0m 56ms/step - accuracy: 0.3231 - loss: 2.0604
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m51s[0m 56ms/step - accuracy: 0.3230 - loss: 2.0604[32m [repeated 294x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m380/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3223 - loss: 2.0353
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m382/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3223 - loss: 2.0353
[1m383/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3223 - loss: 2.0353
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m26s[0m 50ms/step - accuracy: 0.3503 - loss: 1.9456
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m26s[0m 50ms/step - accuracy: 0.3504 - loss: 1.9455
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m25s[0m 50ms/step - accuracy: 0.3504 - loss: 1.9455
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 28ms/step - accuracy: 0.2718 - loss: 2.1815
[1m 873/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 28ms/step - accuracy: 0.2718 - loss: 2.1815[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 28ms/step - accuracy: 0.2717 - loss: 2.1817[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2482 - loss: 2.3176 
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2482 - loss: 2.3176
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m422/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 46ms/step - accuracy: 0.2922 - loss: 2.1339[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m455/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 40ms/step - accuracy: 0.3230 - loss: 2.0342
[1m457/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3230 - loss: 2.0341[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m329/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.2195 - loss: 2.4290
[1m330/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.2195 - loss: 2.4290[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m341/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m11s[0m 47ms/step - accuracy: 0.2195 - loss: 2.4292[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.3509 - loss: 1.9439
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.3510 - loss: 1.9438
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m23s[0m 51ms/step - accuracy: 0.3510 - loss: 1.9438
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.1807 - loss: 2.5791 - val_accuracy: 0.2633 - val_loss: 2.2731
[36m(train_cnn_ray_tune pid=2697856)[0m Epoch 13/29
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:21[0m 123ms/step - accuracy: 0.1250 - loss: 2.1549
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 45ms/step - accuracy: 0.1424 - loss: 2.3536  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 39ms/step - accuracy: 0.1467 - loss: 2.4451
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m47s[0m 57ms/step - accuracy: 0.3195 - loss: 2.0627[32m [repeated 302x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m26s[0m 34ms/step - accuracy: 0.1946 - loss: 2.4646
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m26s[0m 34ms/step - accuracy: 0.1947 - loss: 2.4644[32m [repeated 219x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m32s[0m 44ms/step - accuracy: 0.2822 - loss: 2.1373
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m32s[0m 44ms/step - accuracy: 0.2822 - loss: 2.1373
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m32s[0m 44ms/step - accuracy: 0.2822 - loss: 2.1374
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 28ms/step - accuracy: 0.2715 - loss: 2.1837
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 28ms/step - accuracy: 0.2715 - loss: 2.1837[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 28ms/step - accuracy: 0.2715 - loss: 2.1838[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m525/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.2926 - loss: 2.1330[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m419/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.2196 - loss: 2.4306
[1m420/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 49ms/step - accuracy: 0.2196 - loss: 2.4306[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m368/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 48ms/step - accuracy: 0.2195 - loss: 2.4297
[1m370/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.2195 - loss: 2.4298 [32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m359/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 48ms/step - accuracy: 0.2195 - loss: 2.4296[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m41s[0m 56ms/step - accuracy: 0.3172 - loss: 2.0633[32m [repeated 245x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 33ms/step - accuracy: 0.1981 - loss: 2.4560
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 33ms/step - accuracy: 0.1981 - loss: 2.4560[32m [repeated 257x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 45ms/step - accuracy: 0.3233 - loss: 2.0337 - val_accuracy: 0.3040 - val_loss: 2.2083
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 24/27
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 112ms/step - accuracy: 0.3125 - loss: 1.9165
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 33ms/step - accuracy: 0.3316 - loss: 1.8775  
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 42ms/step - accuracy: 0.2589 - loss: 2.2413
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 42ms/step - accuracy: 0.2589 - loss: 2.2413[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 42ms/step - accuracy: 0.2590 - loss: 2.2413[32m [repeated 82x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m535/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 48ms/step - accuracy: 0.2199 - loss: 2.4322[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2317 - loss: 2.3314 
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2317 - loss: 2.3314
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m537/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 48ms/step - accuracy: 0.2199 - loss: 2.4323
[1m539/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 47ms/step - accuracy: 0.2199 - loss: 2.4323[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 62/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.3367 - loss: 1.9725
[1m 64/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.3366 - loss: 1.9730[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 66/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.3366 - loss: 1.9735[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m37s[0m 32ms/step - accuracy: 0.2714 - loss: 2.1849 - val_accuracy: 0.2940 - val_loss: 2.1686
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:13[0m 127ms/step - accuracy: 0.2188 - loss: 1.9690
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m21s[0m 44ms/step - accuracy: 0.2841 - loss: 2.1427[32m [repeated 216x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m24s[0m 43ms/step - accuracy: 0.1720 - loss: 2.7033
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m24s[0m 43ms/step - accuracy: 0.1720 - loss: 2.7033[32m [repeated 190x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 51ms/step - accuracy: 0.2500 - loss: 2.4129  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.2929 - loss: 2.1322 - val_accuracy: 0.3200 - val_loss: 2.1806
[36m(train_cnn_ray_tune pid=2697817)[0m Epoch 10/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.2433 - loss: 2.2954 
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47[0m 93ms/step - accuracy: 0.2500 - loss: 2.1752
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 29ms/step - accuracy: 0.2743 - loss: 2.1478 
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 42ms/step - accuracy: 0.2592 - loss: 2.2413
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 42ms/step - accuracy: 0.2592 - loss: 2.2413[32m [repeated 96x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 28ms/step - accuracy: 0.2312 - loss: 2.3313[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 47ms/step - accuracy: 0.2199 - loss: 2.4331[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m568/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 47ms/step - accuracy: 0.2199 - loss: 2.4329
[1m569/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 47ms/step - accuracy: 0.2199 - loss: 2.4329[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m31s[0m 53ms/step - accuracy: 0.2199 - loss: 2.4331 - val_accuracy: 0.2732 - val_loss: 2.2496
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:14[0m 129ms/step - accuracy: 0.0625 - loss: 2.7742
[1m  2/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 58ms/step - accuracy: 0.1016 - loss: 2.6849  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 87/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 48ms/step - accuracy: 0.3002 - loss: 2.0918
[1m 88/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 48ms/step - accuracy: 0.3003 - loss: 2.0918
[1m 89/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 48ms/step - accuracy: 0.3004 - loss: 2.0918
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 60ms/step - accuracy: 0.1267 - loss: 2.6249
[1m  4/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 62ms/step - accuracy: 0.1419 - loss: 2.5896[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 95/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m23s[0m 48ms/step - accuracy: 0.3007 - loss: 2.0918[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.2483 - loss: 2.3190 - val_accuracy: 0.3075 - val_loss: 2.1516[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:54[0m 100ms/step - accuracy: 0.3125 - loss: 2.4486[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 28ms/step - accuracy: 0.2309 - loss: 2.3313
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 28ms/step - accuracy: 0.2309 - loss: 2.3313
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 28ms/step - accuracy: 0.2309 - loss: 2.3313
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m25s[0m 40ms/step - accuracy: 0.2700 - loss: 2.2183[32m [repeated 210x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m29s[0m 55ms/step - accuracy: 0.3162 - loss: 2.0603
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m29s[0m 55ms/step - accuracy: 0.3162 - loss: 2.0603[32m [repeated 191x across cluster][0m
Trial status: 3 TERMINATED | 17 RUNNING
Current time: 2025-11-07 12:51:22. Total running time: 11min 1s
Logical resource usage: 17.0/20 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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  3                 1          0.000190495         29                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m16s[0m 44ms/step - accuracy: 0.2845 - loss: 2.1436
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m16s[0m 44ms/step - accuracy: 0.2845 - loss: 2.1436
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m16s[0m 44ms/step - accuracy: 0.2845 - loss: 2.1436
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 48ms/step - accuracy: 0.2917 - loss: 2.2857  
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 21/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.2005 - loss: 2.4542
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 32ms/step - accuracy: 0.2005 - loss: 2.4542[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m5s[0m 51ms/step - accuracy: 0.3538 - loss: 1.9363[32m [repeated 109x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m109/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 47ms/step - accuracy: 0.2035 - loss: 2.4546
[1m110/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m22s[0m 47ms/step - accuracy: 0.2036 - loss: 2.4544[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m195/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m18s[0m 49ms/step - accuracy: 0.3029 - loss: 2.0917[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m328/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9962
[1m330/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9962
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m332/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9963
[1m334/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9963
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m336/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9963
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m54s[0m 47ms/step - accuracy: 0.2593 - loss: 2.2413 - val_accuracy: 0.2980 - val_loss: 2.1114
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m338/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9964
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m340/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9964
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:17[0m 119ms/step - accuracy: 0.3125 - loss: 1.7839
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m342/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9964
[1m344/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9964
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:09[0m 60ms/step - accuracy: 0.2812 - loss: 1.8295 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:07[0m 58ms/step - accuracy: 0.2569 - loss: 1.8766
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 42ms/step - accuracy: 0.2745 - loss: 2.1955
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 42ms/step - accuracy: 0.2745 - loss: 2.1955
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 42ms/step - accuracy: 0.2745 - loss: 2.1956
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m346/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9965
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 47ms/step - accuracy: 0.2429 - loss: 1.9625 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.2406 - loss: 1.9958
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m348/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9965
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m350/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9966
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m352/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9966
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m354/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9966
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m218/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 49ms/step - accuracy: 0.3028 - loss: 2.0917
[1m219/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 49ms/step - accuracy: 0.3028 - loss: 2.0917
[1m220/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m17s[0m 49ms/step - accuracy: 0.3028 - loss: 2.0917
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m356/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9967
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m358/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9967
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m14s[0m 42ms/step - accuracy: 0.1711 - loss: 2.7060[32m [repeated 239x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m24s[0m 55ms/step - accuracy: 0.3161 - loss: 2.0589
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m24s[0m 55ms/step - accuracy: 0.3161 - loss: 2.0589[32m [repeated 168x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m360/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9968
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m362/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9968
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m364/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9968
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 29ms/step - accuracy: 0.2651 - loss: 2.1854
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 29ms/step - accuracy: 0.2651 - loss: 2.1854
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m22s[0m 28ms/step - accuracy: 0.2651 - loss: 2.1855
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m366/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9969
[1m368/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9969
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m370/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9970
[1m372/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9970
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m374/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9970
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 42ms/step - accuracy: 0.1710 - loss: 2.7062
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 42ms/step - accuracy: 0.1710 - loss: 2.7062
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 42ms/step - accuracy: 0.1710 - loss: 2.7062
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m376/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9971
[1m378/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9971
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m380/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9972
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m382/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9972
[1m383/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9972
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m385/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9973
[1m387/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9973
[36m(train_cnn_ray_tune pid=2697835)[0m Epoch 12/16
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m389/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9973
[1m391/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9974
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m392/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9974
[1m394/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9974
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m396/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9975
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 51ms/step - accuracy: 0.3544 - loss: 1.9347
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 51ms/step - accuracy: 0.3544 - loss: 1.9347[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m Epoch 14/28
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m398/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9975
[1m400/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9975
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:48[0m 94ms/step - accuracy: 0.3125 - loss: 2.1261
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.2917 - loss: 2.0860 
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m402/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9976
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m404/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9976
[1m405/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9976
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 43ms/step - accuracy: 0.1709 - loss: 2.7065
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 43ms/step - accuracy: 0.1709 - loss: 2.7065
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m12s[0m 43ms/step - accuracy: 0.1709 - loss: 2.7065
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m406/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9977
[1m408/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9977
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 51ms/step - accuracy: 0.3544 - loss: 1.9345[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m409/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9977
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m411/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9978
[1m412/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9978
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m414/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9978
[1m415/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9978
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m417/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9978
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m419/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9979
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m421/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9979
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m423/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9979
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m425/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9980
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m427/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9980
[1m429/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9980
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 43ms/step - accuracy: 0.2465 - loss: 2.3067  
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m431/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9981
[1m433/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9981
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m435/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9982
[1m436/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9982
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m438/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9982
[1m440/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9982
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m442/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9983
[1m444/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9983
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m445/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9983
[1m446/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9984
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m294/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 49ms/step - accuracy: 0.3024 - loss: 2.0919
[1m296/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 49ms/step - accuracy: 0.3023 - loss: 2.0920[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m448/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9984
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m450/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9984
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m451/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9985
[1m452/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9985
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m234/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m15s[0m 45ms/step - accuracy: 0.2123 - loss: 2.4462[32m [repeated 54x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m454/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9985
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m456/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9985
[1m458/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9986
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m460/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9986
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m462/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9986
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m464/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9987
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m55s[0m 48ms/step - accuracy: 0.2744 - loss: 2.1957 - val_accuracy: 0.3087 - val_loss: 2.1953[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m466/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9987
[1m468/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9987
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:11[0m 114ms/step - accuracy: 0.2500 - loss: 2.4240
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m470/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9987
[1m472/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9988
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m473/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9988
[1m475/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 39ms/step - accuracy: 0.3348 - loss: 1.9988
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m477/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9988
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m479/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9989
[1m481/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9989
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m483/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9989
[1m485/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9989
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m487/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9990
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m489/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9990
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 285/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m43s[0m 50ms/step - accuracy: 0.2818 - loss: 2.1882[32m [repeated 246x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m19s[0m 55ms/step - accuracy: 0.3161 - loss: 2.0576
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m19s[0m 55ms/step - accuracy: 0.3161 - loss: 2.0576[32m [repeated 223x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m491/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9990
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m493/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9990
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m495/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9991
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m497/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9991
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 42ms/step - accuracy: 0.1708 - loss: 2.7072
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 42ms/step - accuracy: 0.1708 - loss: 2.7072
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m8s[0m 42ms/step - accuracy: 0.1708 - loss: 2.7072
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m499/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9991
[1m501/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9991
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m503/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9991
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m505/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9992
[1m507/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9992
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m509/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9992
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m511/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9992
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m513/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9992
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m514/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9993
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m516/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9993
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m518/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9993
[1m519/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9993
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m521/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 39ms/step - accuracy: 0.3347 - loss: 1.9993
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m523/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9994
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m525/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9994
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 42ms/step - accuracy: 0.1708 - loss: 2.7074
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 42ms/step - accuracy: 0.1708 - loss: 2.7074[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m Epoch 12/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m527/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9994
[1m529/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9994
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:38[0m 86ms/step - accuracy: 0.2500 - loss: 2.3301
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 23ms/step - accuracy: 0.2214 - loss: 2.3725 
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m531/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9995
[1m532/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9995
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m534/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9995
[1m535/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9995
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m537/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9995
[1m539/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9995
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m4s[0m 44ms/step - accuracy: 0.2850 - loss: 2.1450[32m [repeated 52x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m541/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9996
[1m542/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9996
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m376/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.3021 - loss: 2.0926
[1m377/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.3021 - loss: 2.0926
[1m378/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 48ms/step - accuracy: 0.3021 - loss: 2.0926
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m550/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9997
[1m552/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 39ms/step - accuracy: 0.3346 - loss: 1.9997
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 29ms/step - accuracy: 0.2664 - loss: 2.1847
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 29ms/step - accuracy: 0.2664 - loss: 2.1847
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m14s[0m 29ms/step - accuracy: 0.2664 - loss: 2.1847
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m335/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 45ms/step - accuracy: 0.2154 - loss: 2.4439
[1m337/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 45ms/step - accuracy: 0.2154 - loss: 2.4438[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m347/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m10s[0m 45ms/step - accuracy: 0.2157 - loss: 2.4435[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m356/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 45ms/step - accuracy: 0.2159 - loss: 2.4432[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m419/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.3019 - loss: 2.0932
[1m421/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m7s[0m 48ms/step - accuracy: 0.3019 - loss: 2.0933[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 37ms/step - accuracy: 0.2010 - loss: 2.4531 - val_accuracy: 0.2664 - val_loss: 2.2584
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:48[0m 94ms/step - accuracy: 0.1250 - loss: 2.5951
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.1111 - loss: 2.5306 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.1151 - loss: 2.4956
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 30ms/step - accuracy: 0.1638 - loss: 2.4320[32m [repeated 230x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m13s[0m 54ms/step - accuracy: 0.3161 - loss: 2.0564
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m13s[0m 54ms/step - accuracy: 0.3161 - loss: 2.0563[32m [repeated 248x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 490ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 4/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step  
[1m 7/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[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=2697864)[0m 
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.2722 - loss: 2.2120 
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 40ms/step - accuracy: 0.2723 - loss: 2.2120
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m13/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 25ms/step
[1m16/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 25ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m19/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m22/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m24/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[1m26/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[1m32/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m35/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[1m37/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m39/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 23ms/step
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 44ms/step - accuracy: 0.3345 - loss: 2.0000 - val_accuracy: 0.3155 - val_loss: 2.1842
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m45/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 23ms/step
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 105ms/step - accuracy: 0.3125 - loss: 2.2759
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.3368 - loss: 2.0295  
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1881 - loss: 2.5427
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.1881 - loss: 2.5427[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 25/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m59/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 24ms/step
[1m62/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 24ms/step
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 23ms/step
[1m76/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m78/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m81/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m84/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m2s[0m 42ms/step - accuracy: 0.1707 - loss: 2.7085[32m [repeated 63x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 28ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 28ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 55ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  4/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step
[1m  6/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m  9/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step
[1m 12/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 14/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 17/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 21ms/step
[1m 19/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 22/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 25/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m3s[0m 23ms/step
[1m 28/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 52/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 40ms/step - accuracy: 0.3335 - loss: 1.9712
[1m 53/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 40ms/step - accuracy: 0.3335 - loss: 1.9715[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 31/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[1m 35/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 37/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[1m 40/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 56/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 40ms/step - accuracy: 0.3335 - loss: 1.9718[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 42/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[1m 45/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 47/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 50/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[1m 53/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 57/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[1m 60/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m531/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.3018 - loss: 2.0945[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 63/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m2s[0m 22ms/step
[1m 66/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m533/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.3018 - loss: 2.0945
[1m535/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 47ms/step - accuracy: 0.3018 - loss: 2.0946[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 69/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[1m 72/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 28ms/step - accuracy: 0.2671 - loss: 2.1847
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 28ms/step - accuracy: 0.2671 - loss: 2.1847
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.2671 - loss: 2.1847
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m66s[0m 57ms/step - accuracy: 0.3545 - loss: 1.9345 - val_accuracy: 0.3234 - val_loss: 2.2201
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 75/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 21ms/step
[1m 77/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 80/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 22ms/step
[1m 83/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 86/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 21ms/step
[1m 89/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.2671 - loss: 2.1847
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.2671 - loss: 2.1847
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.2671 - loss: 2.1848
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 92/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m 95/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 21ms/step
[1m 98/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m101/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m1s[0m 21ms/step
[1m104/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m107/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 21ms/step
[1m110/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m1s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2560 - loss: 2.3220[32m [repeated 266x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 31ms/step - accuracy: 0.1994 - loss: 2.4232
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m29s[0m 31ms/step - accuracy: 0.1995 - loss: 2.4232[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m113/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 21ms/step
[1m116/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m119/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 21ms/step
[1m122/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m125/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 21ms/step
[1m127/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m130/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 21ms/step
[1m133/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m136/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 21ms/step
[1m138/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m141/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 21ms/step
[1m144/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m147/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m150/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 21ms/step
[1m152/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m154/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697863)[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=2697863)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697863)[0m 
[1m157/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 22ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 22ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:51:43. Total running time: 11min 22s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             679.655 │
│ time_total_s                 679.655 │
│ training_iteration                 1 │
│ val_accuracy                 0.32341 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:51:43. Total running time: 11min 22s
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 54ms/step - accuracy: 0.3161 - loss: 2.0552
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 54ms/step - accuracy: 0.3161 - loss: 2.0552[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m57s[0m 49ms/step - accuracy: 0.2851 - loss: 2.1455 - val_accuracy: 0.3548 - val_loss: 2.1063
[36m(train_cnn_ray_tune pid=2697862)[0m Epoch 12/27
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:01[0m 105ms/step - accuracy: 0.2500 - loss: 2.2487
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 30ms/step - accuracy: 0.2001 - loss: 2.4224
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 30ms/step - accuracy: 0.2002 - loss: 2.4224
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m27s[0m 30ms/step - accuracy: 0.2002 - loss: 2.4224
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 29ms/step - accuracy: 0.2951 - loss: 2.1427  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.2971 - loss: 2.1394
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 54ms/step - accuracy: 0.3161 - loss: 2.0551[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m192/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 37ms/step - accuracy: 0.3304 - loss: 1.9958
[1m194/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 37ms/step - accuracy: 0.3303 - loss: 1.9959[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m196/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 37ms/step - accuracy: 0.3303 - loss: 1.9960[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 30ms/step - accuracy: 0.1999 - loss: 2.4252
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 30ms/step - accuracy: 0.1999 - loss: 2.4253
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m24s[0m 30ms/step - accuracy: 0.1999 - loss: 2.4253
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m573/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 44ms/step - accuracy: 0.2195 - loss: 2.4385[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m575/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 44ms/step - accuracy: 0.2195 - loss: 2.4385
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 44ms/step - accuracy: 0.2195 - loss: 2.4384[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.2733 - loss: 2.2095
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.2733 - loss: 2.2095
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 40ms/step - accuracy: 0.2733 - loss: 2.2094
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.1250 - loss: 2.5928 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.1388 - loss: 2.5618
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 38ms/step - accuracy: 0.2753 - loss: 2.1246[32m [repeated 175x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 30ms/step - accuracy: 0.2000 - loss: 2.4261
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m23s[0m 30ms/step - accuracy: 0.2000 - loss: 2.4262[32m [repeated 191x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 56ms/step - accuracy: 0.3017 - loss: 2.0952 - val_accuracy: 0.2988 - val_loss: 2.2055
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 97ms/step - accuracy: 0.1562 - loss: 2.4239
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 42ms/step - accuracy: 0.1892 - loss: 2.2884
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 53ms/step - accuracy: 0.3162 - loss: 2.0542
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 53ms/step - accuracy: 0.3162 - loss: 2.0541[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m55s[0m 47ms/step - accuracy: 0.1707 - loss: 2.7088 - val_accuracy: 0.2184 - val_loss: 2.3660
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 22/28[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:41[0m 88ms/step - accuracy: 0.1250 - loss: 2.6229
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 53ms/step - accuracy: 0.3162 - loss: 2.0541[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2562 - loss: 2.3149 
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2562 - loss: 2.3149
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 55/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2927 - loss: 2.1094
[1m 57/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2933 - loss: 2.1086[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 63/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2952 - loss: 2.1057[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m375/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 34ms/step - accuracy: 0.3309 - loss: 1.9977[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m50s[0m 44ms/step - accuracy: 0.2736 - loss: 2.2088 - val_accuracy: 0.3053 - val_loss: 2.1713
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m381/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 34ms/step - accuracy: 0.3309 - loss: 1.9977
[1m383/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 34ms/step - accuracy: 0.3309 - loss: 1.9977[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:33[0m 81ms/step - accuracy: 0.2500 - loss: 2.1178

Trial status: 4 TERMINATED | 16 RUNNING
Current time: 2025-11-07 12:51:52. Total running time: 11min 31s
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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000190495         29        1            679.655         0.323407 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.3125 - loss: 2.0540 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 33ms/step - accuracy: 0.3094 - loss: 2.0716
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m16s[0m 28ms/step - accuracy: 0.2002 - loss: 2.4306[32m [repeated 169x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 32ms/step - accuracy: 0.3726 - loss: 1.8944
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m13s[0m 32ms/step - accuracy: 0.3726 - loss: 1.8944[32m [repeated 227x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m28s[0m 49ms/step - accuracy: 0.2196 - loss: 2.4384 - val_accuracy: 0.2724 - val_loss: 2.2429
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:29[0m 78ms/step - accuracy: 0.1875 - loss: 2.6901
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 34ms/step - accuracy: 0.1389 - loss: 2.7214 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 24ms/step - accuracy: 0.2282 - loss: 2.3368
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 24ms/step - accuracy: 0.2282 - loss: 2.3368[32m [repeated 59x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m Epoch 14/29[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 24ms/step - accuracy: 0.2282 - loss: 2.3368[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 24ms/step - accuracy: 0.2281 - loss: 2.3368
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 24ms/step - accuracy: 0.2281 - loss: 2.3368
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 24ms/step - accuracy: 0.2281 - loss: 2.3368
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.2002 - loss: 2.4316
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.2002 - loss: 2.4316
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.2002 - loss: 2.4316
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.3730 - loss: 1.8949 
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.3730 - loss: 1.8949
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m184/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 38ms/step - accuracy: 0.3027 - loss: 2.0940
[1m186/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 38ms/step - accuracy: 0.3027 - loss: 2.0941[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m201/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 37ms/step - accuracy: 0.2260 - loss: 2.4333[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   2/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.3281 - loss: 1.8239 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.3090 - loss: 1.8602
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.2885 - loss: 1.9082 
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m543/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 33ms/step - accuracy: 0.3320 - loss: 1.9977[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m68s[0m 59ms/step - accuracy: 0.3162 - loss: 2.0541 - val_accuracy: 0.3232 - val_loss: 2.1216[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m535/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 33ms/step - accuracy: 0.3319 - loss: 1.9978
[1m537/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 33ms/step - accuracy: 0.3319 - loss: 1.9978[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:55[0m 100ms/step - accuracy: 0.3125 - loss: 1.8541
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 49ms/step - accuracy: 0.3013 - loss: 2.0145[32m [repeated 202x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 28ms/step - accuracy: 0.2005 - loss: 2.4322
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 28ms/step - accuracy: 0.2005 - loss: 2.4323[32m [repeated 261x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 34ms/step - accuracy: 0.2555 - loss: 2.3119
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 34ms/step - accuracy: 0.2555 - loss: 2.3118[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m Epoch 10/23
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2007 - loss: 2.4326[32m [repeated 53x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2006 - loss: 2.4326 
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2007 - loss: 2.4326
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.2821 - loss: 2.1876 
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 46ms/step - accuracy: 0.2821 - loss: 2.1876
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 39ms/step - accuracy: 0.3322 - loss: 1.9975 - val_accuracy: 0.3173 - val_loss: 2.1837
[36m(train_cnn_ray_tune pid=2697884)[0m Epoch 26/27
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m316/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2290 - loss: 2.4268 
[1m318/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2290 - loss: 2.4267
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m306/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 40ms/step - accuracy: 0.3023 - loss: 2.0987
[1m308/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 40ms/step - accuracy: 0.3022 - loss: 2.0988[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 106ms/step - accuracy: 0.2812 - loss: 2.1190
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.3177 - loss: 2.0949  
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.3075 - loss: 2.1060
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m312/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 40ms/step - accuracy: 0.3022 - loss: 2.0989[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m329/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2292 - loss: 2.4264[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m335/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2293 - loss: 2.4262
[1m337/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.2293 - loss: 2.4261[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 28ms/step - accuracy: 0.2281 - loss: 2.3363 - val_accuracy: 0.2815 - val_loss: 2.2270
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 420ms/step
[1m 5/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 13ms/step  
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 9/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m20/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m24/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 35ms/step - accuracy: 0.1775 - loss: 2.6967[32m [repeated 218x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 46ms/step - accuracy: 0.3176 - loss: 2.0346
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 46ms/step - accuracy: 0.3176 - loss: 2.0346[32m [repeated 183x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m33/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m37/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m44/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.2009 - loss: 2.4332
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.2009 - loss: 2.4332
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.2009 - loss: 2.4332
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 14ms/step
[1m57/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 14ms/step
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m78/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m83/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 18ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 19ms/step
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 28ms/step - accuracy: 0.2010 - loss: 2.4335
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 28ms/step - accuracy: 0.2010 - loss: 2.4335[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 61ms/step
[1m  7/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 14/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 9ms/step 
[1m 19/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 23/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 28/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.1910 - loss: 2.3857  
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 32/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 36/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 28ms/step - accuracy: 0.2010 - loss: 2.4336[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 41/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 46/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 50/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 54/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 59/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 63/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 68/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 72/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 76/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 81/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m 85/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 89/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m 93/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m 97/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697874)[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=2697874)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m100/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 13ms/step
[1m105/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m109/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 13ms/step
[1m113/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m118/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m122/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m127/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m131/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 13ms/step
[1m136/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 14/27
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m139/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 13ms/step
[1m144/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m130/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.3105 - loss: 2.0438
[1m133/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.3107 - loss: 2.0432[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:00[0m 104ms/step - accuracy: 0.2500 - loss: 2.1554
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m149/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 13ms/step
[1m153/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m157/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697874)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m124/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m17s[0m 38ms/step - accuracy: 0.3102 - loss: 2.0451[32m [repeated 39x across cluster][0m

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:52:06. Total running time: 11min 45s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             702.225 │
│ time_total_s                 702.225 │
│ training_iteration                 1 │
│ val_accuracy                 0.28152 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:52:06. Total running time: 11min 45s
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m432/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 41ms/step - accuracy: 0.3018 - loss: 2.1012[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m434/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 41ms/step - accuracy: 0.3018 - loss: 2.1012
[1m436/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 41ms/step - accuracy: 0.3018 - loss: 2.1012[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m44s[0m 38ms/step - accuracy: 0.2555 - loss: 2.3118 - val_accuracy: 0.3216 - val_loss: 2.1489
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.2729 - loss: 2.1790
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.2729 - loss: 2.1790
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m14s[0m 26ms/step - accuracy: 0.2729 - loss: 2.1789
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 36ms/step - accuracy: 0.1781 - loss: 2.6949[32m [repeated 197x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m42s[0m 47ms/step - accuracy: 0.3218 - loss: 2.0314
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m42s[0m 47ms/step - accuracy: 0.3218 - loss: 2.0314[32m [repeated 144x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.2621 - loss: 2.2292
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.2621 - loss: 2.2292[32m [repeated 94x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 46ms/step - accuracy: 0.2820 - loss: 2.1871[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 36ms/step - accuracy: 0.3741 - loss: 1.8945 - val_accuracy: 0.3492 - val_loss: 2.0591
[36m(train_cnn_ray_tune pid=2697873)[0m Epoch 15/28
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m283/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.3176 - loss: 2.0284
[1m285/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.3177 - loss: 2.0282[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:49[0m 95ms/step - accuracy: 0.1875 - loss: 2.2372
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 26ms/step - accuracy: 0.2569 - loss: 2.0764 
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m272/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.3171 - loss: 2.0294[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m307/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.3186 - loss: 2.0262[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m558/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.3023 - loss: 2.1009
[1m560/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 41ms/step - accuracy: 0.3023 - loss: 2.1009[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.1785 - loss: 2.6931[32m [repeated 183x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m36s[0m 46ms/step - accuracy: 0.3238 - loss: 2.0288
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m36s[0m 46ms/step - accuracy: 0.3238 - loss: 2.0288[32m [repeated 181x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 25ms/step - accuracy: 0.2734 - loss: 2.1759
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 25ms/step - accuracy: 0.2734 - loss: 2.1758[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 44ms/step - accuracy: 0.2304 - loss: 2.4199 - val_accuracy: 0.2668 - val_loss: 2.2386
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 92ms/step - accuracy: 0.3125 - loss: 2.3973
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m7s[0m 25ms/step - accuracy: 0.2734 - loss: 2.1759[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 32ms/step - accuracy: 0.2986 - loss: 2.0357 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.2854 - loss: 2.1414
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 25ms/step - accuracy: 0.2733 - loss: 2.1753
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 25ms/step - accuracy: 0.2733 - loss: 2.1753
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 25ms/step - accuracy: 0.2733 - loss: 2.1752
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 42ms/step - accuracy: 0.2621 - loss: 2.2291 - val_accuracy: 0.3107 - val_loss: 2.1059[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 22/28[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 47/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2270 - loss: 2.3945
[1m 48/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2266 - loss: 2.3950[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:06[0m 115ms/step - accuracy: 0.2812 - loss: 1.9673
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 31ms/step - accuracy: 0.2743 - loss: 2.0208  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 24/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2648 - loss: 2.1184[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m466/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.3229 - loss: 2.0166[32m [repeated 19x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m480/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.3232 - loss: 2.0159
[1m482/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.3233 - loss: 2.0158[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 39ms/step - accuracy: 0.2847 - loss: 1.9836  
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 35ms/step - accuracy: 0.2828 - loss: 2.1761[32m [repeated 157x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m29s[0m 44ms/step - accuracy: 0.3253 - loss: 2.0251
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m29s[0m 44ms/step - accuracy: 0.3253 - loss: 2.0251[32m [repeated 241x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1892 - loss: 2.5339 
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1892 - loss: 2.5339
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1892 - loss: 2.5340
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1892 - loss: 2.5340[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 46ms/step - accuracy: 0.3024 - loss: 2.1007 - val_accuracy: 0.2877 - val_loss: 2.2024
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:10[0m 113ms/step - accuracy: 0.1875 - loss: 2.0559[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 43ms/step - accuracy: 0.3224 - loss: 2.0993
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 44ms/step - accuracy: 0.3219 - loss: 2.0999
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 44ms/step - accuracy: 0.3214 - loss: 2.1005
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 25ms/step - accuracy: 0.2733 - loss: 2.1747[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m49s[0m 42ms/step - accuracy: 0.2713 - loss: 2.1926 - val_accuracy: 0.3194 - val_loss: 2.2026[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m Epoch 13/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m174/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m15s[0m 39ms/step - accuracy: 0.2199 - loss: 2.4172
[1m175/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m15s[0m 39ms/step - accuracy: 0.2199 - loss: 2.4173[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:28[0m 128ms/step - accuracy: 0.3125 - loss: 1.8249
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 36ms/step - accuracy: 0.3264 - loss: 1.9003  
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m149/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 41ms/step - accuracy: 0.2907 - loss: 2.1043[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m559/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3250 - loss: 2.0122[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m576/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3254 - loss: 2.0114
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 33ms/step - accuracy: 0.3254 - loss: 2.0113[32m [repeated 14x across cluster][0m

Trial status: 5 TERMINATED | 15 RUNNING
Current time: 2025-11-07 12:52:22. Total running time: 12min 1s
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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18        1            702.225         0.281517 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000190495         29        1            679.655         0.323407 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m24s[0m 44ms/step - accuracy: 0.3261 - loss: 2.0233[32m [repeated 215x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 27ms/step - accuracy: 0.2083 - loss: 2.4194
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m22s[0m 27ms/step - accuracy: 0.2084 - loss: 2.4194[32m [repeated 155x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.3255 - loss: 2.0113 - val_accuracy: 0.3135 - val_loss: 2.1742
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m223/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 39ms/step - accuracy: 0.2207 - loss: 2.4183
[1m224/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 39ms/step - accuracy: 0.2208 - loss: 2.4183
[1m226/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 39ms/step - accuracy: 0.2208 - loss: 2.4183
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 418ms/step
[36m(train_cnn_ray_tune pid=2697884)[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=2697884)[0m 
[1m13/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2924 - loss: 2.1728 
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.2924 - loss: 2.1728
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m17/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[1m20/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m25/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m28/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m35/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m39/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 35ms/step - accuracy: 0.1783 - loss: 2.6917
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 35ms/step - accuracy: 0.1783 - loss: 2.6917[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 16ms/step
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m77/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 16ms/step
[1m80/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 37ms/step - accuracy: 0.2880 - loss: 2.1312[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m83/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 32ms/step - accuracy: 0.1896 - loss: 2.5349
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 32ms/step - accuracy: 0.1896 - loss: 2.5349
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 32ms/step - accuracy: 0.1896 - loss: 2.5349
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:37[0m 84ms/step - accuracy: 0.2500 - loss: 2.1969
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2969 - loss: 1.9722 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2968 - loss: 1.9893
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 20ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 21ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 56ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m  6/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m  9/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 13/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step
[1m 17/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 21/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 24/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 27/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 31/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 35/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 39/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 43/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 47/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 51/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 28ms/step - accuracy: 0.2733 - loss: 2.1746 - val_accuracy: 0.2974 - val_loss: 2.1639
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 19/24
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m253/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 42ms/step - accuracy: 0.2961 - loss: 2.0995
[1m255/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 42ms/step - accuracy: 0.2961 - loss: 2.0995[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 57/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 61/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 66/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 70/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 27ms/step - accuracy: 0.2978 - loss: 2.0905
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 27ms/step - accuracy: 0.2970 - loss: 2.0932
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 27ms/step - accuracy: 0.2963 - loss: 2.0960
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m313/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 39ms/step - accuracy: 0.2221 - loss: 2.4191[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 74/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 79/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 84/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 88/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 91/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 94/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m321/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2221 - loss: 2.4193 
[1m323/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2222 - loss: 2.4193
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m 98/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m102/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[1m106/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[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=2697884)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m325/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2222 - loss: 2.4193
[1m327/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2222 - loss: 2.4194
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m111/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 14ms/step
[1m114/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m329/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2222 - loss: 2.4194
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m118/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[1m121/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m331/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2222 - loss: 2.4194
[1m333/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2222 - loss: 2.4195
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m125/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[1m129/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m335/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2222 - loss: 2.4195
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m133/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[1m137/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m337/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2223 - loss: 2.4195
[1m339/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2223 - loss: 2.4196
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m140/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[1m144/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m341/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2223 - loss: 2.4196
[1m343/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2223 - loss: 2.4197
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m148/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m153/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m345/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 39ms/step - accuracy: 0.2223 - loss: 2.4197
[36m(train_cnn_ray_tune pid=2697884)[0m 
[1m157/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m347/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2223 - loss: 2.4198
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m349/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2224 - loss: 2.4198

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:52:28. Total running time: 12min 6s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             723.629 │
│ time_total_s                 723.629 │
│ training_iteration                 1 │
│ val_accuracy                 0.31348 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:52:28. Total running time: 12min 6s
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m19s[0m 44ms/step - accuracy: 0.3264 - loss: 2.0223[32m [repeated 210x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 28ms/step - accuracy: 0.2107 - loss: 2.4181
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m18s[0m 28ms/step - accuracy: 0.2108 - loss: 2.4180[32m [repeated 164x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m351/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2224 - loss: 2.4199
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m259/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 42ms/step - accuracy: 0.2962 - loss: 2.0993
[1m260/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 42ms/step - accuracy: 0.2963 - loss: 2.0993
[1m261/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 42ms/step - accuracy: 0.2963 - loss: 2.0993
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m353/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2224 - loss: 2.4199
[1m355/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2224 - loss: 2.4200
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m357/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2224 - loss: 2.4200
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m358/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2224 - loss: 2.4200
[1m360/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2224 - loss: 2.4201
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m362/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2224 - loss: 2.4201
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m364/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2224 - loss: 2.4201
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m366/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2225 - loss: 2.4201
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m368/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2225 - loss: 2.4202
[1m370/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 39ms/step - accuracy: 0.2225 - loss: 2.4202
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m372/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2225 - loss: 2.4202
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m374/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2225 - loss: 2.4202
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m375/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2225 - loss: 2.4202
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m377/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2225 - loss: 2.4202
[1m379/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2225 - loss: 2.4203
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m381/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2225 - loss: 2.4203
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m383/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2225 - loss: 2.4203
[1m385/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2226 - loss: 2.4203
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.2924 - loss: 2.1721
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.2924 - loss: 2.1721[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m387/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2226 - loss: 2.4203
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m389/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2226 - loss: 2.4203
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m391/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2226 - loss: 2.4203
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.2924 - loss: 2.1720[32m [repeated 74x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m334/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 41ms/step - accuracy: 0.2980 - loss: 2.0975
[1m336/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 41ms/step - accuracy: 0.2980 - loss: 2.0974[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m332/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 42ms/step - accuracy: 0.2980 - loss: 2.0975[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 24ms/step - accuracy: 0.2811 - loss: 2.1530
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m21s[0m 24ms/step - accuracy: 0.2810 - loss: 2.1532
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m20s[0m 24ms/step - accuracy: 0.2810 - loss: 2.1533
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m338/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.2981 - loss: 2.0974 
[1m340/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 41ms/step - accuracy: 0.2981 - loss: 2.0974
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m48s[0m 41ms/step - accuracy: 0.2882 - loss: 2.1314 - val_accuracy: 0.3464 - val_loss: 2.0877
[36m(train_cnn_ray_tune pid=2697862)[0m Epoch 13/27
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:41[0m 88ms/step - accuracy: 0.3750 - loss: 1.7198
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m410/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 41ms/step - accuracy: 0.2995 - loss: 2.0966[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 34ms/step - accuracy: 0.3333 - loss: 1.9624 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.3175 - loss: 2.0401
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m412/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 41ms/step - accuracy: 0.2995 - loss: 2.0966
[1m414/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 41ms/step - accuracy: 0.2995 - loss: 2.0966[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m13s[0m 44ms/step - accuracy: 0.3268 - loss: 2.0211[32m [repeated 174x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 337/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 23ms/step - accuracy: 0.2803 - loss: 2.1567
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m19s[0m 23ms/step - accuracy: 0.2803 - loss: 2.1568[32m [repeated 203x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:40[0m 87ms/step - accuracy: 0.2500 - loss: 2.2904
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.2326 - loss: 2.4029 
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.2588 - loss: 2.2771
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.2588 - loss: 2.2771[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.3729 - loss: 1.8743[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 27ms/step - accuracy: 0.2120 - loss: 2.4156
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 27ms/step - accuracy: 0.2120 - loss: 2.4156
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m10s[0m 27ms/step - accuracy: 0.2120 - loss: 2.4156[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.3270 - loss: 2.0203 
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m9s[0m 44ms/step - accuracy: 0.3270 - loss: 2.0203
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m43s[0m 37ms/step - accuracy: 0.2924 - loss: 2.1720 - val_accuracy: 0.3254 - val_loss: 2.1708[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 14/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:52[0m 97ms/step - accuracy: 0.1250 - loss: 3.0250
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m533/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 40ms/step - accuracy: 0.3008 - loss: 2.0962[32m [repeated 48x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 28ms/step - accuracy: 0.1354 - loss: 3.0508 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 29ms/step - accuracy: 0.1394 - loss: 3.0055
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m535/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 40ms/step - accuracy: 0.3008 - loss: 2.0962
[1m537/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 40ms/step - accuracy: 0.3008 - loss: 2.0962[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 144/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 31ms/step - accuracy: 0.1923 - loss: 2.5288[32m [repeated 244x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 24ms/step - accuracy: 0.2796 - loss: 2.1630
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 24ms/step - accuracy: 0.2796 - loss: 2.1630[32m [repeated 191x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m21s[0m 36ms/step - accuracy: 0.2906 - loss: 2.1436
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:54[0m 99ms/step - accuracy: 0.2500 - loss: 2.2962
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m45s[0m 39ms/step - accuracy: 0.2361 - loss: 2.2645 
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 27ms/step - accuracy: 0.2120 - loss: 2.4142
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 27ms/step - accuracy: 0.2120 - loss: 2.4142[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 44ms/step - accuracy: 0.2236 - loss: 2.4178 - val_accuracy: 0.2722 - val_loss: 2.2342
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.2604 - loss: 2.3087
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.2669 - loss: 2.2869
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  7/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2676 - loss: 2.2917
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m6s[0m 43ms/step - accuracy: 0.3271 - loss: 2.0202[32m [repeated 87x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  9/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 40ms/step - accuracy: 0.2642 - loss: 2.3008
[1m 11/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2608 - loss: 2.3055
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 12/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 40ms/step - accuracy: 0.2599 - loss: 2.3053
[1m 14/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 40ms/step - accuracy: 0.2588 - loss: 2.3096
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 16/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 40ms/step - accuracy: 0.2578 - loss: 2.3154
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 18/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2573 - loss: 2.3206
[1m 20/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 39ms/step - accuracy: 0.2577 - loss: 2.3231
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 22/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 39ms/step - accuracy: 0.2573 - loss: 2.3271
[1m 24/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 39ms/step - accuracy: 0.2566 - loss: 2.3311
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 26/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.2557 - loss: 2.3355
[1m 28/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2547 - loss: 2.3399
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 30/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 38ms/step - accuracy: 0.2540 - loss: 2.3431
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 32/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2537 - loss: 2.3452
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 34/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2536 - loss: 2.3467
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 36/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2535 - loss: 2.3477
[1m 38/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2531 - loss: 2.3488
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 40/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2529 - loss: 2.3495
[1m 41/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2527 - loss: 2.3501
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 43/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2525 - loss: 2.3511
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 45/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2522 - loss: 2.3523
[1m 47/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2519 - loss: 2.3538
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 49/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2517 - loss: 2.3549
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2514 - loss: 2.3559
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 53/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2510 - loss: 2.3570
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 55/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2506 - loss: 2.3580
[1m 57/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2503 - loss: 2.3589
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 59/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2500 - loss: 2.3599
[1m 61/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2499 - loss: 2.3607
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 63/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2498 - loss: 2.3615
[1m 65/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2496 - loss: 2.3624
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 23/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 67/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2494 - loss: 2.3634
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 107ms/step - accuracy: 0.3750 - loss: 2.1279
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 30ms/step - accuracy: 0.3403 - loss: 2.1692  
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 69/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2491 - loss: 2.3644
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.3011 - loss: 2.0959[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 71/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2489 - loss: 2.3653
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 73/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2487 - loss: 2.3662
[1m 74/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2485 - loss: 2.3667
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m566/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.3010 - loss: 2.0960
[1m568/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 40ms/step - accuracy: 0.3011 - loss: 2.0960[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m21s[0m 41ms/step - accuracy: 0.2907 - loss: 2.1499[32m [repeated 178x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 35ms/step - accuracy: 0.1731 - loss: 2.7038
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m30s[0m 34ms/step - accuracy: 0.1731 - loss: 2.7037[32m [repeated 204x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m52s[0m 92ms/step - accuracy: 0.2500 - loss: 2.3447
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.2118 - loss: 2.4139
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.2117 - loss: 2.4139
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.2117 - loss: 2.4139
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.2117 - loss: 2.4139
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.2117 - loss: 2.4139
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.2117 - loss: 2.4139
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.2117 - loss: 2.4139
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.2117 - loss: 2.4139[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 46ms/step - accuracy: 0.3012 - loss: 2.0959 - val_accuracy: 0.3262 - val_loss: 2.1623
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 69/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 39ms/step - accuracy: 0.3157 - loss: 2.1060
[1m 70/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 40ms/step - accuracy: 0.3156 - loss: 2.1056[32m [repeated 21x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m143/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.2448 - loss: 2.3823[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 43ms/step - accuracy: 0.3271 - loss: 2.0199[32m [repeated 89x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 35ms/step - accuracy: 0.2594 - loss: 2.2770 - val_accuracy: 0.3109 - val_loss: 2.1344
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 15/27
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:49[0m 95ms/step - accuracy: 0.5000 - loss: 1.7340
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 26ms/step - accuracy: 0.3924 - loss: 2.0219 
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m24s[0m 35ms/step - accuracy: 0.2874 - loss: 2.1357[32m [repeated 156x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 27ms/step - accuracy: 0.2752 - loss: 2.2139
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 27ms/step - accuracy: 0.2752 - loss: 2.2140[32m [repeated 196x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2868 - loss: 2.1501 
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2867 - loss: 2.1501
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 18/26
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:28[0m 77ms/step - accuracy: 0.2500 - loss: 2.3973
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.2361 - loss: 2.4234 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2208 - loss: 2.5023
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m22s[0m 34ms/step - accuracy: 0.2876 - loss: 2.1354
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m22s[0m 34ms/step - accuracy: 0.2876 - loss: 2.1354
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m22s[0m 34ms/step - accuracy: 0.2876 - loss: 2.1354
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 23ms/step - accuracy: 0.2798 - loss: 2.1642
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 23ms/step - accuracy: 0.2798 - loss: 2.1642[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 365ms/step
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 6/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step  
[1m11/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m291/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.2415 - loss: 2.3944
[1m293/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2415 - loss: 2.3945
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m17/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m23/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m295/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2415 - loss: 2.3945
[1m297/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2414 - loss: 2.3946
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m28/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m32/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m218/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.3109 - loss: 2.0834
[1m220/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.3109 - loss: 2.0832[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m222/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.3109 - loss: 2.0831[32m [repeated 39x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m299/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2414 - loss: 2.3946
[1m301/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2414 - loss: 2.3947
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m37/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 34ms/step - accuracy: 0.2738 - loss: 2.2060[32m [repeated 37x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m38s[0m 33ms/step - accuracy: 0.3741 - loss: 1.8746 - val_accuracy: 0.3339 - val_loss: 2.1130[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m303/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2413 - loss: 2.3947
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m305/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2413 - loss: 2.3948
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m307/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2413 - loss: 2.3948
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 11ms/step
[1m61/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m309/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2412 - loss: 2.3949
[1m311/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2412 - loss: 2.3949
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 11ms/step
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m313/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2412 - loss: 2.3950
[1m315/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2412 - loss: 2.3950
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 12ms/step
[1m78/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m317/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2411 - loss: 2.3950
[1m319/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2411 - loss: 2.3950
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m82/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m321/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2411 - loss: 2.3951
[1m323/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2411 - loss: 2.3951
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m325/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2410 - loss: 2.3951
[1m327/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2410 - loss: 2.3951
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m329/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2410 - loss: 2.3952
[1m331/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2409 - loss: 2.3952
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m333/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2409 - loss: 2.3952
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m335/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2409 - loss: 2.3953
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m337/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2408 - loss: 2.3953
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 53ms/step
[1m  7/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m339/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2408 - loss: 2.3954
[1m341/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2408 - loss: 2.3954
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 12/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m343/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2407 - loss: 2.3955
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 17/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 23/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m345/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2407 - loss: 2.3955
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 27/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 31/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m347/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2407 - loss: 2.3956
[1m349/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2406 - loss: 2.3956
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 36/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 40/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m351/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2406 - loss: 2.3957
[1m353/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2405 - loss: 2.3957
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 44/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m 48/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m355/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2405 - loss: 2.3958
[1m357/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2405 - loss: 2.3958
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 52/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 57/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m359/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2404 - loss: 2.3959
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 62/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m361/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2404 - loss: 2.3959
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 66/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m363/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2404 - loss: 2.3959
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 71/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m365/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2403 - loss: 2.3960
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 76/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m 82/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m367/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2403 - loss: 2.3960
[1m369/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2402 - loss: 2.3960
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m290/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.3109 - loss: 2.0789 
[1m292/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.3109 - loss: 2.0788
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 87/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 11ms/step
[1m 92/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m371/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 34ms/step - accuracy: 0.2402 - loss: 2.3961
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.2188 - loss: 1.9973 
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m 96/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 11ms/step
[1m101/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m106/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 11ms/step
[1m110/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m114/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 12ms/step
[1m118/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 12ms/step

Trial status: 6 TERMINATED | 14 RUNNING
Current time: 2025-11-07 12:52:52. Total running time: 12min 31s
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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18        1            702.225         0.281517 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27        1            723.629         0.31348  │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000190495         29        1            679.655         0.323407 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m122/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step
[1m125/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m129/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m133/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[1m137/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697873)[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=2697873)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m141/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 12ms/step
[1m145/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m149/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m153/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step
[1m157/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 39ms/step - accuracy: 0.2852 - loss: 2.0472[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 32ms/step - accuracy: 0.1711 - loss: 2.6963
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 32ms/step - accuracy: 0.1711 - loss: 2.6963[32m [repeated 218x across cluster][0m
[36m(train_cnn_ray_tune pid=2697873)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 13ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:52:53. Total running time: 12min 32s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s              749.19 │
│ time_total_s                  749.19 │
│ training_iteration                 1 │
│ val_accuracy                 0.33393 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:52:53. Total running time: 12min 32s
[36m(train_cnn_ray_tune pid=2697836)[0m Epoch 11/23
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47[0m 93ms/step - accuracy: 0.0625 - loss: 2.1926
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m3s[0m 34ms/step - accuracy: 0.2854 - loss: 2.1525
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 34ms/step - accuracy: 0.2854 - loss: 2.1525[32m [repeated 75x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 20/24
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m355/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.3108 - loss: 2.0769
[1m357/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.3108 - loss: 2.0769[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:40[0m 87ms/step - accuracy: 0.1875 - loss: 2.1595
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m286/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.3109 - loss: 2.0790
[1m288/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.3109 - loss: 2.0790[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m284/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.3109 - loss: 2.0791[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 39ms/step - accuracy: 0.2894 - loss: 2.1545[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 26ms/step - accuracy: 0.2799 - loss: 2.1639 - val_accuracy: 0.3139 - val_loss: 2.1899[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m450/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 34ms/step - accuracy: 0.2387 - loss: 2.3973[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2266 - loss: 2.1650 
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 24ms/step - accuracy: 0.2162 - loss: 2.4099
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 24ms/step - accuracy: 0.2162 - loss: 2.4098
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m17s[0m 24ms/step - accuracy: 0.2163 - loss: 2.4097
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 153/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 23ms/step - accuracy: 0.2715 - loss: 2.1234[32m [repeated 164x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 39ms/step - accuracy: 0.3230 - loss: 2.0065
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 39ms/step - accuracy: 0.3231 - loss: 2.0062[32m [repeated 201x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 28ms/step - accuracy: 0.2083 - loss: 2.2851 
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2932 - loss: 2.1673 
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2932 - loss: 2.1672
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2932 - loss: 2.1671
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2933 - loss: 2.1670[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m Epoch 14/16
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m498/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 35ms/step - accuracy: 0.3099 - loss: 2.0757
[1m500/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 35ms/step - accuracy: 0.3099 - loss: 2.0757[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:41[0m 88ms/step - accuracy: 0.2500 - loss: 2.2596
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.1845 - loss: 2.5347
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.1845 - loss: 2.5347
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m6s[0m 28ms/step - accuracy: 0.1845 - loss: 2.5347
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 28ms/step - accuracy: 0.1845 - loss: 2.5347[32m [repeated 56x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m44s[0m 38ms/step - accuracy: 0.2733 - loss: 2.2069 - val_accuracy: 0.3206 - val_loss: 2.0876
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m510/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 35ms/step - accuracy: 0.3098 - loss: 2.0756[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 24ms/step - accuracy: 0.2167 - loss: 2.4061
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 24ms/step - accuracy: 0.2167 - loss: 2.4061
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 24ms/step - accuracy: 0.2167 - loss: 2.4060
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.2372 - loss: 2.3975 - val_accuracy: 0.2775 - val_loss: 2.2265
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 25/28
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m49s[0m 86ms/step - accuracy: 0.1562 - loss: 2.5227
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 31ms/step - accuracy: 0.1667 - loss: 2.5097
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.1713 - loss: 2.4946
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m44s[0m 38ms/step - accuracy: 0.2849 - loss: 2.1532 - val_accuracy: 0.3081 - val_loss: 2.2021
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  7/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.1781 - loss: 2.4706
[1m  9/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.1874 - loss: 2.4500
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45[0m 91ms/step - accuracy: 0.3750 - loss: 1.8136
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 26ms/step - accuracy: 0.3993 - loss: 1.8470 
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 11/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.1942 - loss: 2.4373
[1m 13/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.2003 - loss: 2.4246
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 15/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.2046 - loss: 2.4190
[1m 17/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.2084 - loss: 2.4137
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 19/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.2115 - loss: 2.4090
[1m 21/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 29ms/step - accuracy: 0.2140 - loss: 2.4054
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 23/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.2163 - loss: 2.4027
[1m 25/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.2177 - loss: 2.4017
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 27/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.2193 - loss: 2.4003
[1m 29/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.2203 - loss: 2.3999
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m16s[0m 22ms/step - accuracy: 0.2820 - loss: 2.1306
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m16s[0m 22ms/step - accuracy: 0.2820 - loss: 2.1308
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m16s[0m 22ms/step - accuracy: 0.2821 - loss: 2.1309
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 31/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.2212 - loss: 2.3994
[1m 33/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.2223 - loss: 2.3984
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m32s[0m 38ms/step - accuracy: 0.3285 - loss: 1.9981[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2170 - loss: 2.4046
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m12s[0m 23ms/step - accuracy: 0.2170 - loss: 2.4046[32m [repeated 176x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 35/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 30ms/step - accuracy: 0.2231 - loss: 2.3978
[1m 37/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.2238 - loss: 2.3970
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 39/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.2245 - loss: 2.3960
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 41/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.2250 - loss: 2.3950
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 43/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.2257 - loss: 2.3940
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 45/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.2261 - loss: 2.3935
[1m 47/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.2265 - loss: 2.3932
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 49/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.2268 - loss: 2.3932
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.2273 - loss: 2.3928
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 53/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 31ms/step - accuracy: 0.2277 - loss: 2.3926
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 55/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2278 - loss: 2.3925
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 57/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2280 - loss: 2.3923
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 59/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2282 - loss: 2.3919
[1m 61/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2283 - loss: 2.3916
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 63/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2284 - loss: 2.3914
[1m 65/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2285 - loss: 2.3914
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 67/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2285 - loss: 2.3914
[1m 69/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2286 - loss: 2.3912
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 71/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2287 - loss: 2.3912
[1m 73/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2288 - loss: 2.3911
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 28ms/step - accuracy: 0.1846 - loss: 2.5344
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 28ms/step - accuracy: 0.1846 - loss: 2.5344[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 75/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2290 - loss: 2.3909
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m571/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.3095 - loss: 2.0754
[1m573/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.3095 - loss: 2.0754[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 77/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2291 - loss: 2.3907
[1m 79/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 32ms/step - accuracy: 0.2292 - loss: 2.3906
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 81/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2294 - loss: 2.3904
[1m 83/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2295 - loss: 2.3903
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 85/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2296 - loss: 2.3903
[1m 87/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2297 - loss: 2.3903
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 28ms/step - accuracy: 0.1847 - loss: 2.5343[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 35ms/step - accuracy: 0.3095 - loss: 2.0754[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 89/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2298 - loss: 2.3904
[1m 91/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2298 - loss: 2.3905
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 93/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2299 - loss: 2.3904
[1m 95/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2300 - loss: 2.3904
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 97/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2301 - loss: 2.3904
[1m 99/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2302 - loss: 2.3903
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m101/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2303 - loss: 2.3902
[1m103/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2304 - loss: 2.3901
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m105/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m15s[0m 32ms/step - accuracy: 0.2305 - loss: 2.3900
[1m107/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 32ms/step - accuracy: 0.2305 - loss: 2.3899
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m109/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 32ms/step - accuracy: 0.2305 - loss: 2.3898
[1m111/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3897
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m114/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m14s[0m 31ms/step - accuracy: 0.2306 - loss: 2.3896
[1m116/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3894
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m119/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3893
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m121/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3893
[1m123/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3893
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m125/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3892
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m127/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3891
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m130/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3889
[1m132/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 31ms/step - accuracy: 0.2309 - loss: 2.3888
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m134/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 31ms/step - accuracy: 0.2309 - loss: 2.3887
[1m136/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 31ms/step - accuracy: 0.2309 - loss: 2.3887
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m138/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 31ms/step - accuracy: 0.2310 - loss: 2.3886
[1m140/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 31ms/step - accuracy: 0.2310 - loss: 2.3886
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m142/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 31ms/step - accuracy: 0.2310 - loss: 2.3885
[1m144/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m13s[0m 31ms/step - accuracy: 0.2311 - loss: 2.3884
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m146/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 31ms/step - accuracy: 0.2311 - loss: 2.3883
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m148/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 31ms/step - accuracy: 0.2311 - loss: 2.3882
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m25s[0m 29ms/step - accuracy: 0.2695 - loss: 2.1911
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m25s[0m 29ms/step - accuracy: 0.2695 - loss: 2.1911
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m25s[0m 29ms/step - accuracy: 0.2695 - loss: 2.1912
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m151/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3882
[1m154/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3882
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m156/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3882
[1m158/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3883
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m160/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3884
[1m162/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3884
[36m(train_cnn_ray_tune pid=2697885)[0m Epoch 14/25
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m164/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3884
[1m166/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3885
[36m(train_cnn_ray_tune pid=2697817)[0m Epoch 12/27
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m168/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3885
[1m170/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3886
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m51s[0m 44ms/step - accuracy: 0.2888 - loss: 2.1561 - val_accuracy: 0.3053 - val_loss: 2.1822
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m172/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3886
[1m174/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2311 - loss: 2.3887
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45[0m 92ms/step - accuracy: 0.3125 - loss: 1.8993
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.3194 - loss: 1.9612 
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m176/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2310 - loss: 2.3888
[1m178/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2310 - loss: 2.3889
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 44ms/step - accuracy: 0.3095 - loss: 2.0754 - val_accuracy: 0.2877 - val_loss: 2.1888
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 99ms/step - accuracy: 0.2812 - loss: 2.1477
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m180/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m12s[0m 30ms/step - accuracy: 0.2310 - loss: 2.3890
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m182/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m12s[0m 31ms/step - accuracy: 0.2310 - loss: 2.3891
[1m184/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m12s[0m 31ms/step - accuracy: 0.2310 - loss: 2.3892
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.2941 - loss: 2.1641
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.2941 - loss: 2.1641
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 29ms/step - accuracy: 0.2941 - loss: 2.1641
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m23s[0m 29ms/step - accuracy: 0.2695 - loss: 2.1916[32m [repeated 98x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 205/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 29ms/step - accuracy: 0.3063 - loss: 2.1051
[1m 207/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 29ms/step - accuracy: 0.3061 - loss: 2.1055[32m [repeated 154x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m190/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m11s[0m 31ms/step - accuracy: 0.2310 - loss: 2.3894[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 31ms/step - accuracy: 0.1847 - loss: 2.5343 - val_accuracy: 0.2617 - val_loss: 2.2606
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 20ms/step - accuracy: 0.2861 - loss: 2.1418
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 20ms/step - accuracy: 0.2861 - loss: 2.1419[32m [repeated 147x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.1840 - loss: 2.1943 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1806 - loss: 2.2923
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 26ms/step - accuracy: 0.2720 - loss: 2.2458[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m261/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3914
[1m263/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3914
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m265/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3915
[1m267/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3915
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m269/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3916
[1m271/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3916
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m273/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3917
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m275/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3917
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m277/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3918
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m280/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3918
[1m282/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3919
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m284/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3919
[1m286/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3920
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m288/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3920
[1m290/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3920
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m292/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3921
[1m294/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3921
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m296/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3921
[1m298/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3922
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m300/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3922
[1m301/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3922
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m303/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3923
[1m305/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3923
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m307/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3923
[1m309/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3924
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  93/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 25ms/step - accuracy: 0.1871 - loss: 2.4892
[1m  95/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 25ms/step - accuracy: 0.1872 - loss: 2.4892
[1m  97/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 25ms/step - accuracy: 0.1873 - loss: 2.4891
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m311/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3924
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m313/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3924
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m315/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3925
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m317/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2308 - loss: 2.3925
[1m319/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3925
[36m(train_cnn_ray_tune pid=2697856)[0m Epoch 16/29[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m321/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3926
[1m323/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3926
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m139/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.3301 - loss: 2.0356
[1m141/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m14s[0m 33ms/step - accuracy: 0.3300 - loss: 2.0357[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m325/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3926
[1m327/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3927
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:53[0m 98ms/step - accuracy: 0.5000 - loss: 1.9533
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 27ms/step - accuracy: 0.3477 - loss: 2.0765 
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m329/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3927
[1m331/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3927
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:33[0m 81ms/step - accuracy: 0.2500 - loss: 1.9775
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m333/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3927
[1m335/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3928
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m337/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3928
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m339/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3928
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.2169 - loss: 2.4044
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.2169 - loss: 2.4044
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 23ms/step - accuracy: 0.2169 - loss: 2.4044
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m341/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3928
[1m343/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3929
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m345/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3929
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m347/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3929
[1m349/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3929
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 145/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 25ms/step - accuracy: 0.1884 - loss: 2.4887[32m [repeated 115x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 35ms/step - accuracy: 0.2859 - loss: 2.1793
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 35ms/step - accuracy: 0.2859 - loss: 2.1791[32m [repeated 124x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m351/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3929
[1m353/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3929
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m161/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 33ms/step - accuracy: 0.3291 - loss: 2.0363[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m355/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3929
[1m357/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3930
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m359/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3930
[1m361/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3930
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m363/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3930
[1m365/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 31ms/step - accuracy: 0.2307 - loss: 2.3930
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:38[0m 85ms/step - accuracy: 0.4375 - loss: 1.5879
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m367/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3930
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 33ms/step - accuracy: 0.4167 - loss: 1.7561 
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m369/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3930
[1m371/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m373/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[1m375/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m377/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[1m379/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m381/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3932
[1m383/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3932
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1910 - loss: 2.6332  
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.1896 - loss: 2.6455
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m385/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3932
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m387/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3932
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m41s[0m 35ms/step - accuracy: 0.1727 - loss: 2.6874 - val_accuracy: 0.2222 - val_loss: 2.3349[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m389/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3932
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 23ms/step - accuracy: 0.2164 - loss: 2.4039
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 23ms/step - accuracy: 0.2164 - loss: 2.4039[32m [repeated 104x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m391/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3932
[1m393/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3932
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m395/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m397/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[1m399/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m401/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[1m403/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 20ms/step - accuracy: 0.2860 - loss: 2.1450[32m [repeated 40x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m405/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m407/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m409/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m411/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[1m413/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m415/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m417/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m419/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2306 - loss: 2.3933
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m421/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3932
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m423/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3932
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m425/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3932
[1m427/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3932
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m429/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3932
[1m431/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3932
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m433/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3932
[1m435/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3932
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m437/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[1m439/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m441/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[1m443/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m445/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[1m447/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m449/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m451/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3931
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m453/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3930
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m455/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3930
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m457/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3930
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m459/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3930
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m461/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3930
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m463/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3929
[1m466/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3929
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m468/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2307 - loss: 2.3929
[1m470/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3929
[36m(train_cnn_ray_tune pid=2697871)[0m Epoch 14/17[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m472/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3928
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m474/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3928
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m282/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.3238 - loss: 2.0410
[1m284/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.3237 - loss: 2.0411[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m476/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3928
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3928
[1m480/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3928
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m482/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3928
[1m484/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3928
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m486/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3927
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m488/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3927
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m490/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3927
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 31ms/step - accuracy: 0.1922 - loss: 2.6441[32m [repeated 172x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.3333 - loss: 1.9894
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m16s[0m 37ms/step - accuracy: 0.3333 - loss: 1.9894[32m [repeated 207x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m500/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 32ms/step - accuracy: 0.2308 - loss: 2.3927
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m290/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 35ms/step - accuracy: 0.3235 - loss: 2.0413 [32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:11[0m 114ms/step - accuracy: 0.1875 - loss: 2.7012
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:37[0m 85ms/step - accuracy: 0.1875 - loss: 2.4969
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m21s[0m 26ms/step - accuracy: 0.1885 - loss: 2.4963
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m20s[0m 26ms/step - accuracy: 0.1885 - loss: 2.4963
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m20s[0m 26ms/step - accuracy: 0.1885 - loss: 2.4964
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1667 - loss: 2.4973 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1862 - loss: 2.4731
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m30s[0m 26ms/step - accuracy: 0.2164 - loss: 2.4039 - val_accuracy: 0.2768 - val_loss: 2.2366
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.2858 - loss: 2.1461
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 20ms/step - accuracy: 0.2858 - loss: 2.1461[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.2712 - loss: 2.2486 - val_accuracy: 0.3139 - val_loss: 2.1272
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 20ms/step - accuracy: 0.2858 - loss: 2.1461[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m375/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.3212 - loss: 2.0444
[1m377/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.3212 - loss: 2.0445[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m389/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 35ms/step - accuracy: 0.3209 - loss: 2.0450[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.3576 - loss: 2.0285 
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 21/24[32m [repeated 3x across cluster][0m

Trial status: 7 TERMINATED | 13 RUNNING
Current time: 2025-11-07 12:53:22. Total running time: 13min 1s
Logical resource usage: 13.0/20 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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28        1            749.19          0.333929 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18        1            702.225         0.281517 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27        1            723.629         0.31348  │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000190495         29        1            679.655         0.323407 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m286/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.3236 - loss: 2.0411
[1m288/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 35ms/step - accuracy: 0.3236 - loss: 2.0412
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m11s[0m 37ms/step - accuracy: 0.3342 - loss: 1.9875[32m [repeated 194x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m27s[0m 31ms/step - accuracy: 0.1887 - loss: 2.6480
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m27s[0m 31ms/step - accuracy: 0.1886 - loss: 2.6481[32m [repeated 278x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:35[0m 82ms/step - accuracy: 0.4375 - loss: 1.8960[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 25ms/step - accuracy: 0.2149 - loss: 2.3875
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 25ms/step - accuracy: 0.2150 - loss: 2.3873
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 25ms/step - accuracy: 0.2152 - loss: 2.3872[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.1771 - loss: 2.3524 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1912 - loss: 2.3189
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.2308 - loss: 2.3922 - val_accuracy: 0.2809 - val_loss: 2.2164
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  5/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 41ms/step - accuracy: 0.2257 - loss: 2.4705
[1m  7/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2181 - loss: 2.4644
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  9/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 39ms/step - accuracy: 0.2171 - loss: 2.4554
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 11/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.2147 - loss: 2.4553
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 13/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.2126 - loss: 2.4574
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 15/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2114 - loss: 2.4590
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2746 - loss: 2.1925
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2746 - loss: 2.1925[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 17/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2102 - loss: 2.4605
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m27s[0m 24ms/step - accuracy: 0.2858 - loss: 2.1461 - val_accuracy: 0.3077 - val_loss: 2.1620
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 19/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2096 - loss: 2.4596
[1m 21/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 37ms/step - accuracy: 0.2093 - loss: 2.4585
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 23/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2097 - loss: 2.4559
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 25/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2106 - loss: 2.4532
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 27/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2115 - loss: 2.4511
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2746 - loss: 2.1926[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 29/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2127 - loss: 2.4482
[1m 31/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2139 - loss: 2.4452
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 33/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2151 - loss: 2.4424
[1m 35/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2166 - loss: 2.4392
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 36/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2171 - loss: 2.4377
[1m 38/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2181 - loss: 2.4348
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 40/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2187 - loss: 2.4325
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 42/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2190 - loss: 2.4307
[1m 44/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2194 - loss: 2.4290
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 46/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2197 - loss: 2.4277
[1m 48/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2198 - loss: 2.4267
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m508/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 36ms/step - accuracy: 0.3192 - loss: 2.0480
[1m510/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 36ms/step - accuracy: 0.3191 - loss: 2.0481[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 50/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2199 - loss: 2.4261
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 52/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2201 - loss: 2.4252
[1m 54/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2202 - loss: 2.4244
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 56/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.2204 - loss: 2.4236
[1m 58/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2206 - loss: 2.4227
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 60/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2208 - loss: 2.4220
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 62/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2211 - loss: 2.4212
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 64/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2214 - loss: 2.4203
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 66/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2216 - loss: 2.4195
[1m 68/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2219 - loss: 2.4187
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m524/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 36ms/step - accuracy: 0.3190 - loss: 2.0483[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 70/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2220 - loss: 2.4179
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 72/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2222 - loss: 2.4173
[1m 74/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2223 - loss: 2.4168
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 76/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2223 - loss: 2.4165
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 78/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2224 - loss: 2.4163
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 80/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2224 - loss: 2.4160
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 82/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2226 - loss: 2.4155
[1m 84/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2227 - loss: 2.4152
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 86/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 37ms/step - accuracy: 0.2229 - loss: 2.4149
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 88/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.2230 - loss: 2.4146
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 90/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 37ms/step - accuracy: 0.2230 - loss: 2.4143
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 92/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2231 - loss: 2.4139
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 26/28
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 94/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2233 - loss: 2.4136
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 96/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2234 - loss: 2.4132
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 98/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2235 - loss: 2.4129
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m100/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2236 - loss: 2.4126
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m102/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2237 - loss: 2.4123
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m104/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2237 - loss: 2.4120
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m106/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2239 - loss: 2.4117
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m108/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2240 - loss: 2.4113
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m110/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2241 - loss: 2.4109
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m112/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2243 - loss: 2.4104
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m114/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2245 - loss: 2.4099
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m116/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2247 - loss: 2.4094
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m118/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2249 - loss: 2.4089
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 25ms/step - accuracy: 0.2142 - loss: 2.3920[32m [repeated 216x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 23ms/step - accuracy: 0.2912 - loss: 2.1727
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m19s[0m 23ms/step - accuracy: 0.2911 - loss: 2.1726[32m [repeated 243x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m120/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2251 - loss: 2.4084
[1m122/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2253 - loss: 2.4078
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m124/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2254 - loss: 2.4073
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m126/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2256 - loss: 2.4067
[1m128/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2258 - loss: 2.4062
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m130/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2259 - loss: 2.4056
[1m132/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m16s[0m 36ms/step - accuracy: 0.2261 - loss: 2.4049
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m134/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2263 - loss: 2.4043
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m136/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2265 - loss: 2.4038
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m58s[0m 101ms/step - accuracy: 0.2812 - loss: 2.3440
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m138/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2267 - loss: 2.4032
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m140/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2268 - loss: 2.4026
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 25ms/step - accuracy: 0.2142 - loss: 2.3920
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 25ms/step - accuracy: 0.2142 - loss: 2.3920
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m19s[0m 25ms/step - accuracy: 0.2142 - loss: 2.3920[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m142/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2270 - loss: 2.4021
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m144/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2271 - loss: 2.4016
[1m146/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2272 - loss: 2.4011
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m148/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2274 - loss: 2.4006
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m150/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2275 - loss: 2.4001
[1m152/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2277 - loss: 2.3996
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m154/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2278 - loss: 2.3991
[1m156/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2279 - loss: 2.3986
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 30ms/step - accuracy: 0.2752 - loss: 2.1926
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 30ms/step - accuracy: 0.2752 - loss: 2.1926[32m [repeated 43x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m158/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 36ms/step - accuracy: 0.2280 - loss: 2.3982
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m160/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.2281 - loss: 2.3978
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m162/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.2282 - loss: 2.3973
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m164/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.2284 - loss: 2.3969
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m166/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.2285 - loss: 2.3965
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m168/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.2286 - loss: 2.3961
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m170/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.2287 - loss: 2.3957
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m172/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.2288 - loss: 2.3953
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m5s[0m 38ms/step - accuracy: 0.3348 - loss: 1.9863[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m174/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.2289 - loss: 2.3949
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m176/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.2290 - loss: 2.3946
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m178/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.2291 - loss: 2.3943
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m180/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.2292 - loss: 2.3939
[1m182/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.2293 - loss: 2.3936
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m184/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2294 - loss: 2.3933
[1m186/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2294 - loss: 2.3930
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m188/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2295 - loss: 2.3928
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m190/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2295 - loss: 2.3926
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m192/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2296 - loss: 2.3924
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m565/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.3186 - loss: 2.0489
[1m567/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.3186 - loss: 2.0489[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m194/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2296 - loss: 2.3922
[1m196/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2296 - loss: 2.3921
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m198/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2296 - loss: 2.3919
[1m200/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2297 - loss: 2.3917
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m202/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2297 - loss: 2.3916
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m204/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2297 - loss: 2.3914
[1m206/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2297 - loss: 2.3913
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 41ms/step - accuracy: 0.3185 - loss: 2.0491 - val_accuracy: 0.3105 - val_loss: 2.1909
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 25/28
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m208/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 35ms/step - accuracy: 0.2297 - loss: 2.3911
[1m210/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.2298 - loss: 2.3910
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 94ms/step - accuracy: 0.4062 - loss: 1.9217
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 37ms/step - accuracy: 0.3750 - loss: 1.9464
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m212/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.2298 - loss: 2.3908
[1m214/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.2298 - loss: 2.3907
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 36ms/step - accuracy: 0.3185 - loss: 2.0490[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m216/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m12s[0m 35ms/step - accuracy: 0.2298 - loss: 2.3906
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m18s[0m 33ms/step - accuracy: 0.2992 - loss: 2.1022[32m [repeated 147x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 32ms/step - accuracy: 0.1834 - loss: 2.6561
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m17s[0m 32ms/step - accuracy: 0.1834 - loss: 2.6561[32m [repeated 216x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 78/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 38ms/step - accuracy: 0.3219 - loss: 2.0448
[1m 80/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 38ms/step - accuracy: 0.3219 - loss: 2.0447[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.3351 - loss: 1.9858
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.3351 - loss: 1.9858[32m [repeated 95x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 86/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 38ms/step - accuracy: 0.3219 - loss: 2.0445[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m299/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2310 - loss: 2.3853 
[1m301/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 36ms/step - accuracy: 0.2310 - loss: 2.3852
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.3351 - loss: 1.9857[32m [repeated 83x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m331/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 36ms/step - accuracy: 0.2312 - loss: 2.3842
[1m333/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 35ms/step - accuracy: 0.2312 - loss: 2.3841[32m [repeated 7x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m359/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 35ms/step - accuracy: 0.2314 - loss: 2.3835[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.2139 - loss: 2.3890 
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.2139 - loss: 2.3890
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.2857 - loss: 2.1630
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.2856 - loss: 2.1630
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.2856 - loss: 2.1630
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 31ms/step - accuracy: 0.1824 - loss: 2.6572[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.2918 - loss: 2.1556
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 36ms/step - accuracy: 0.2919 - loss: 2.1556[32m [repeated 198x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 34ms/step - accuracy: 0.2758 - loss: 2.1922 - val_accuracy: 0.3057 - val_loss: 2.1178
[36m(train_cnn_ray_tune pid=2697835)[0m Epoch 15/16
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 80ms/step - accuracy: 0.3750 - loss: 1.9862
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.4167 - loss: 1.9385 
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m441/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 34ms/step - accuracy: 0.2319 - loss: 2.3817
[1m443/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 34ms/step - accuracy: 0.2320 - loss: 2.3817
[1m445/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 34ms/step - accuracy: 0.2320 - loss: 2.3816
[36m(train_cnn_ray_tune pid=2697871)[0m ��━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 31ms/step - accuracy: 0.1821 - loss: 2.6576
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m240/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 33ms/step - accuracy: 0.3206 - loss: 2.0437
[1m242/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m11s[0m 33ms/step - accuracy: 0.3206 - loss: 2.0437[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.2852 - loss: 2.1624
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.2852 - loss: 2.1624[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m196/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.3222 - loss: 2.0425[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m5s[0m 21ms/step - accuracy: 0.2850 - loss: 2.1620[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m276/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.3196 - loss: 2.0450 
[1m278/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.3195 - loss: 2.0451
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 36ms/step - accuracy: 0.3403 - loss: 1.6734 
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m291/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.3192 - loss: 2.0454
[1m294/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 33ms/step - accuracy: 0.3192 - loss: 2.0455[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m310/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 33ms/step - accuracy: 0.3188 - loss: 2.0459[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1820 - loss: 2.6576 
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.1820 - loss: 2.6577
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  62/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 39ms/step - accuracy: 0.3724 - loss: 1.8646[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  64/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 39ms/step - accuracy: 0.3720 - loss: 1.8667
[1m  66/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 39ms/step - accuracy: 0.3714 - loss: 1.8688[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 35ms/step - accuracy: 0.2869 - loss: 2.1418 - val_accuracy: 0.3117 - val_loss: 2.1699[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m Epoch 15/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2:04[0m 108ms/step - accuracy: 0.3125 - loss: 2.0168
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.2639 - loss: 2.0824  
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 28ms/step - accuracy: 0.2980 - loss: 2.1437
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 28ms/step - accuracy: 0.2980 - loss: 2.1437
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 28ms/step - accuracy: 0.2980 - loss: 2.1437
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45[0m 91ms/step - accuracy: 0.3750 - loss: 1.6408
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m272/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.3197 - loss: 2.0449
[1m274/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 33ms/step - accuracy: 0.3196 - loss: 2.0449[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:39[0m 87ms/step - accuracy: 0.2500 - loss: 2.4499
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2109 - loss: 2.4449 
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 23ms/step - accuracy: 0.2134 - loss: 2.3884
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 23ms/step - accuracy: 0.2134 - loss: 2.3884[32m [repeated 204x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 21ms/step - accuracy: 0.2842 - loss: 2.1607[32m [repeated 126x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m436/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 34ms/step - accuracy: 0.3178 - loss: 2.0469
[1m438/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 34ms/step - accuracy: 0.3178 - loss: 2.0469[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m456/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 34ms/step - accuracy: 0.3177 - loss: 2.0471[32m [repeated 28x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 42ms/step - accuracy: 0.2324 - loss: 2.3803 - val_accuracy: 0.2823 - val_loss: 2.2144
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 202/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 37ms/step - accuracy: 0.3556 - loss: 1.9192[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 204/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 37ms/step - accuracy: 0.3555 - loss: 1.9194
[1m 206/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m35s[0m 37ms/step - accuracy: 0.3555 - loss: 1.9196[32m [repeated 107x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m35s[0m 30ms/step - accuracy: 0.1862 - loss: 2.5146 - val_accuracy: 0.2688 - val_loss: 2.2557
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 27/28[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 27ms/step - accuracy: 0.2619 - loss: 2.2613
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 27ms/step - accuracy: 0.2619 - loss: 2.2613
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 27ms/step - accuracy: 0.2619 - loss: 2.2612
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m37s[0m 32ms/step - accuracy: 0.2979 - loss: 2.1435 - val_accuracy: 0.3065 - val_loss: 2.1868
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 69ms/step - accuracy: 0.1250 - loss: 2.2410
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 35/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 28ms/step - accuracy: 0.2005 - loss: 2.4439
[1m 37/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 29ms/step - accuracy: 0.2016 - loss: 2.4400[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 106ms/step - accuracy: 0.0938 - loss: 2.6704
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.1389 - loss: 2.6131  
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.1736 - loss: 2.2919 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2311 - loss: 2.2468
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2760 - loss: 2.2442 
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 31ms/step - accuracy: 0.2992 - loss: 2.1008
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 31ms/step - accuracy: 0.2992 - loss: 2.1008[32m [repeated 123x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 47/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 29ms/step - accuracy: 0.2054 - loss: 2.4265
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 26ms/step - accuracy: 0.2627 - loss: 2.2600[32m [repeated 72x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m574/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3177 - loss: 2.0481
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3177 - loss: 2.0481[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m114/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m13s[0m 28ms/step - accuracy: 0.2225 - loss: 2.3879
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m117/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.2227 - loss: 2.3876
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m564/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3177 - loss: 2.0480[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m123/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.2233 - loss: 2.3867
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m125/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.2235 - loss: 2.3864
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m127/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m12s[0m 28ms/step - accuracy: 0.2237 - loss: 2.3862
Trial status: 7 TERMINATED | 13 RUNNING
Current time: 2025-11-07 12:53:52. Total running time: 13min 31s
Logical resource usage: 13.0/20 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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28        1            749.19          0.333929 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18        1            702.225         0.281517 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27        1            723.629         0.31348  │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000190495         29        1            679.655         0.323407 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.3177 - loss: 2.0481 - val_accuracy: 0.2962 - val_loss: 2.1880
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 366/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m27s[0m 34ms/step - accuracy: 0.3536 - loss: 1.9275[32m [repeated 97x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 18ms/step - accuracy: 0.2923 - loss: 2.1277
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 18ms/step - accuracy: 0.2922 - loss: 2.1279[32m [repeated 208x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m Epoch 15/17[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:31[0m 80ms/step - accuracy: 0.2500 - loss: 2.2921
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.2917 - loss: 2.1470 
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 231/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 20ms/step - accuracy: 0.2124 - loss: 2.4126
[1m 233/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 20ms/step - accuracy: 0.2123 - loss: 2.4126
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m18s[0m 20ms/step - accuracy: 0.2122 - loss: 2.4125
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m40s[0m 35ms/step - accuracy: 0.2992 - loss: 2.1008 - val_accuracy: 0.3538 - val_loss: 2.0824[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42[0m 89ms/step - accuracy: 0.3125 - loss: 2.1006[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m206/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 29ms/step - accuracy: 0.2278 - loss: 2.3818
[1m208/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m10s[0m 29ms/step - accuracy: 0.2278 - loss: 2.3818[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.2778 - loss: 2.4557 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 25ms/step - accuracy: 0.2648 - loss: 2.5097[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m42s[0m 37ms/step - accuracy: 0.3160 - loss: 2.1339 
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.2627 - loss: 2.2601
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 26ms/step - accuracy: 0.2627 - loss: 2.2600[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 47/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.3373 - loss: 2.0039[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m254/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2287 - loss: 2.3796
[1m256/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2288 - loss: 2.3795
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m258/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2288 - loss: 2.3794
[1m260/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2288 - loss: 2.3794
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m262/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2289 - loss: 2.3793
[1m264/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2289 - loss: 2.3792
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m268/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2289 - loss: 2.3791
[1m270/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2290 - loss: 2.3790
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m272/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2290 - loss: 2.3790
[1m274/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2290 - loss: 2.3789
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m276/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2290 - loss: 2.3789[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m278/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2290 - loss: 2.3788
[1m280/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2291 - loss: 2.3788
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m282/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2291 - loss: 2.3787
[1m284/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2291 - loss: 2.3787
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m288/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2291 - loss: 2.3786
[1m290/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2291 - loss: 2.3786
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m298/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2292 - loss: 2.3784
[1m300/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2292 - loss: 2.3783
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m302/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2292 - loss: 2.3783
[1m304/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2292 - loss: 2.3782
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m308/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2293 - loss: 2.3781
[1m310/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2293 - loss: 2.3781
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m23s[0m 36ms/step - accuracy: 0.3541 - loss: 1.9301[32m [repeated 223x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 33ms/step - accuracy: 0.1853 - loss: 2.6972
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 32ms/step - accuracy: 0.1853 - loss: 2.6971[32m [repeated 295x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m322/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 31ms/step - accuracy: 0.2293 - loss: 2.3778
[1m324/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2293 - loss: 2.3778
[36m(train_cnn_ray_tune pid=2697862)[0m Epoch 15/27[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m326/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2294 - loss: 2.3778
[1m328/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2294 - loss: 2.3778
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:38[0m 85ms/step - accuracy: 0.4375 - loss: 2.0314
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 31ms/step - accuracy: 0.3715 - loss: 2.1258 
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m336/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2294 - loss: 2.3776
[1m338/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 31ms/step - accuracy: 0.2294 - loss: 2.3776
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m346/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.2295 - loss: 2.3774
[1m348/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.2295 - loss: 2.3773
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m173/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 37ms/step - accuracy: 0.3356 - loss: 2.0110
[1m175/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m15s[0m 37ms/step - accuracy: 0.3355 - loss: 2.0112[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 20ms/step - accuracy: 0.2900 - loss: 2.1282
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 20ms/step - accuracy: 0.2900 - loss: 2.1282
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m13s[0m 20ms/step - accuracy: 0.2900 - loss: 2.1282
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m181/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m14s[0m 37ms/step - accuracy: 0.3353 - loss: 2.0117[32m [repeated 38x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m359/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.2296 - loss: 2.3770
[1m361/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2296 - loss: 2.3770
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m369/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2297 - loss: 2.3768
[1m371/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2297 - loss: 2.3768
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m383/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2298 - loss: 2.3765
[1m385/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2299 - loss: 2.3764
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m389/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2299 - loss: 2.3763
[1m391/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m6s[0m 32ms/step - accuracy: 0.2299 - loss: 2.3763
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m393/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2299 - loss: 2.3762
[1m395/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2300 - loss: 2.3762
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m397/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2300 - loss: 2.3761
[1m399/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2300 - loss: 2.3761
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m403/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2300 - loss: 2.3760
[1m405/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2301 - loss: 2.3759
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m407/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2301 - loss: 2.3758
[1m409/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2301 - loss: 2.3758
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m411/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2301 - loss: 2.3757
[1m413/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2302 - loss: 2.3757
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m415/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2302 - loss: 2.3756
[1m417/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.2302 - loss: 2.3755
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m401/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m5s[0m 32ms/step - accuracy: 0.2300 - loss: 2.3760[32m [repeated 31x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m425/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2303 - loss: 2.3753
[1m426/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2303 - loss: 2.3753
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m428/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2303 - loss: 2.3752
[1m429/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2303 - loss: 2.3752
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m431/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2304 - loss: 2.3751
[1m433/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2304 - loss: 2.3751
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m434/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2304 - loss: 2.3750
[1m436/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2304 - loss: 2.3750
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2860 - loss: 2.1742
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2860 - loss: 2.1742
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m444/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2305 - loss: 2.3747
[1m446/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2305 - loss: 2.3746
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2860 - loss: 2.1743
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2860 - loss: 2.1743
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2860 - loss: 2.1744
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2902 - loss: 2.1295
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2902 - loss: 2.1296
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2902 - loss: 2.1296
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m450/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2305 - loss: 2.3745
[1m452/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 33ms/step - accuracy: 0.2306 - loss: 2.3744
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2860 - loss: 2.1744
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2860 - loss: 2.1745
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2860 - loss: 2.1745
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2860 - loss: 2.1746
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 37ms/step - accuracy: 0.3547 - loss: 1.9323[32m [repeated 295x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.2132 - loss: 2.3995
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m13s[0m 24ms/step - accuracy: 0.2132 - loss: 2.3994[32m [repeated 260x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2860 - loss: 2.1746
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m460/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2306 - loss: 2.3742
[1m462/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2307 - loss: 2.3741
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2860 - loss: 2.1747
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2859 - loss: 2.1747
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2859 - loss: 2.1747
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2859 - loss: 2.1748
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2859 - loss: 2.1748
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2859 - loss: 2.1749
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m470/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2307 - loss: 2.3739
[1m472/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2307 - loss: 2.3739
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 30ms/step - accuracy: 0.2859 - loss: 2.1749
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.2902 - loss: 2.1297 
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.2902 - loss: 2.1297
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2859 - loss: 2.1749
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m476/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2308 - loss: 2.3738
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2308 - loss: 2.3737
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2859 - loss: 2.1750
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m8s[0m 30ms/step - accuracy: 0.2859 - loss: 2.1751
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m298/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.3311 - loss: 2.0226
[1m300/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.3311 - loss: 2.0228[32m [repeated 20x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m486/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2308 - loss: 2.3735
[1m488/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2309 - loss: 2.3735
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m490/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 33ms/step - accuracy: 0.2309 - loss: 2.3734
[1m492/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 33ms/step - accuracy: 0.2309 - loss: 2.3734
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m306/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.3309 - loss: 2.0232[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m503/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 33ms/step - accuracy: 0.2310 - loss: 2.3732
[1m505/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 33ms/step - accuracy: 0.2310 - loss: 2.3731
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m507/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 33ms/step - accuracy: 0.2310 - loss: 2.3731
[1m509/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 33ms/step - accuracy: 0.2310 - loss: 2.3730
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.2902 - loss: 2.1303
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.2902 - loss: 2.1304
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.2902 - loss: 2.1304
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m345/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 38ms/step - accuracy: 0.3297 - loss: 2.0257
[1m347/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 38ms/step - accuracy: 0.3296 - loss: 2.0258[32m [repeated 8x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m362/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m8s[0m 38ms/step - accuracy: 0.3293 - loss: 2.0265[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.2902 - loss: 2.1311
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.2902 - loss: 2.1311[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.2152 - loss: 2.3943[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m22s[0m 33ms/step - accuracy: 0.1824 - loss: 2.6735[32m [repeated 206x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 37ms/step - accuracy: 0.3545 - loss: 1.9344
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m15s[0m 37ms/step - accuracy: 0.3545 - loss: 1.9344[32m [repeated 203x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2931 - loss: 2.1409 
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.2931 - loss: 2.1409
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m315/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m10s[0m 38ms/step - accuracy: 0.3306 - loss: 2.0238
[1m317/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 38ms/step - accuracy: 0.3305 - loss: 2.0239 [32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.2153 - loss: 2.3940
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.2154 - loss: 2.3940
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.2154 - loss: 2.3939
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 39ms/step - accuracy: 0.2315 - loss: 2.3717 - val_accuracy: 0.2773 - val_loss: 2.2180
[36m(train_cnn_ray_tune pid=2697883)[0m Epoch 28/28
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 98ms/step - accuracy: 0.3125 - loss: 2.1171
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  3/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 38ms/step - accuracy: 0.2760 - loss: 2.2225
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m477/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 38ms/step - accuracy: 0.3270 - loss: 2.0318
[1m479/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 38ms/step - accuracy: 0.3270 - loss: 2.0319[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  9/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2572 - loss: 2.3169
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 11/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2532 - loss: 2.3335
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 13/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 36ms/step - accuracy: 0.2506 - loss: 2.3438
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m495/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 38ms/step - accuracy: 0.3267 - loss: 2.0323[32m [repeated 36x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 27/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 35ms/step - accuracy: 0.2412 - loss: 2.3700
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 29/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 35ms/step - accuracy: 0.2403 - loss: 2.3711
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 31/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 35ms/step - accuracy: 0.2395 - loss: 2.3725
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 41/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 35ms/step - accuracy: 0.2374 - loss: 2.3728
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 43/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2370 - loss: 2.3729
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 45/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.2366 - loss: 2.3729
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 24ms/step - accuracy: 0.2168 - loss: 2.3909
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m4s[0m 24ms/step - accuracy: 0.2168 - loss: 2.3908[32m [repeated 134x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2358 - loss: 2.3731
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 53/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2355 - loss: 2.3731
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 31ms/step - accuracy: 0.2851 - loss: 2.1783[32m [repeated 118x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 54/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2354 - loss: 2.3730
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 56/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2352 - loss: 2.3728
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 58/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.2350 - loss: 2.3727
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m24s[0m 39ms/step - accuracy: 0.3012 - loss: 2.1196[32m [repeated 168x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.3086 - loss: 2.0797
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m19s[0m 34ms/step - accuracy: 0.3086 - loss: 2.0797[32m [repeated 133x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 76/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2343 - loss: 2.3695
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 78/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2343 - loss: 2.3692
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 80/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 35ms/step - accuracy: 0.2342 - loss: 2.3690
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 82/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 35ms/step - accuracy: 0.2342 - loss: 2.3689
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 84/578[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2341 - loss: 2.3687
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 90/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 35ms/step - accuracy: 0.2340 - loss: 2.3679
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 92/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2339 - loss: 2.3676
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 94/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 35ms/step - accuracy: 0.2338 - loss: 2.3674
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 96/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2337 - loss: 2.3673
[1m 98/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.2335 - loss: 2.3674[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m108/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m16s[0m 35ms/step - accuracy: 0.2330 - loss: 2.3677
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m122/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.2322 - loss: 2.3686
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m140/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.2314 - loss: 2.3693
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m142/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m15s[0m 35ms/step - accuracy: 0.2314 - loss: 2.3695
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.3083 - loss: 2.0801
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.3083 - loss: 2.0801
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m16s[0m 34ms/step - accuracy: 0.3083 - loss: 2.0801
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m148/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 35ms/step - accuracy: 0.2312 - loss: 2.3698
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m574/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.3259 - loss: 2.0339
[1m576/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 38ms/step - accuracy: 0.3259 - loss: 2.0339[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2719 - loss: 2.2363 
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 29ms/step - accuracy: 0.2719 - loss: 2.2363
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m170/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.2308 - loss: 2.3703
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m172/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.2308 - loss: 2.3704
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 38ms/step - accuracy: 0.3259 - loss: 2.0340[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m174/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.2307 - loss: 2.3705
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m176/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.2307 - loss: 2.3705
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m178/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 34ms/step - accuracy: 0.2306 - loss: 2.3705
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m25s[0m 43ms/step - accuracy: 0.3259 - loss: 2.0340 - val_accuracy: 0.3167 - val_loss: 2.1867
[36m(train_cnn_ray_tune pid=2697872)[0m Epoch 27/28
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m200/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.2304 - loss: 2.3705
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 25ms/step - accuracy: 0.2903 - loss: 2.1326 - val_accuracy: 0.2867 - val_loss: 2.1699
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 80ms/step - accuracy: 0.3125 - loss: 2.1861
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m202/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m12s[0m 34ms/step - accuracy: 0.2303 - loss: 2.3705
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 29ms/step - accuracy: 0.3061 - loss: 2.1175
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 29ms/step - accuracy: 0.3061 - loss: 2.1175[32m [repeated 144x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3607 - loss: 2.0005 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3956 - loss: 1.9204
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 31ms/step - accuracy: 0.2929 - loss: 2.1407[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 34ms/step - accuracy: 0.3083 - loss: 2.0804[32m [repeated 89x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m18s[0m 38ms/step - accuracy: 0.3008 - loss: 2.1218
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m18s[0m 38ms/step - accuracy: 0.3008 - loss: 2.1218[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 50/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m18s[0m 36ms/step - accuracy: 0.3339 - loss: 2.0376
[1m 52/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m19s[0m 36ms/step - accuracy: 0.3342 - loss: 2.0368[32m [repeated 35x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2474 - loss: 2.3799 
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m284/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2305 - loss: 2.3692 
[1m286/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2305 - loss: 2.3692
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m12s[0m 32ms/step - accuracy: 0.1820 - loss: 2.6615
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 32ms/step - accuracy: 0.1820 - loss: 2.6615
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m11s[0m 32ms/step - accuracy: 0.1820 - loss: 2.6614[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1820 - loss: 2.6596
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1820 - loss: 2.6595
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 32ms/step - accuracy: 0.1820 - loss: 2.6595
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 94/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m17s[0m 36ms/step - accuracy: 0.3349 - loss: 2.0283[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m292/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2305 - loss: 2.3690
[1m294/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.2305 - loss: 2.3690[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m318/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m8s[0m 34ms/step - accuracy: 0.2306 - loss: 2.3684[32m [repeated 8x across cluster][0m
Trial status: 7 TERMINATED | 13 RUNNING
Current time: 2025-11-07 12:54:22. Total running time: 14min 1s
Logical resource usage: 13.0/20 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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    RUNNING              3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28        1            749.19          0.333929 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18        1            702.225         0.281517 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27        1            723.629         0.31348  │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000190495         29        1            679.655         0.323407 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 21/26[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 28ms/step - accuracy: 0.2176 - loss: 2.3888 - val_accuracy: 0.2910 - val_loss: 2.2280[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43[0m 89ms/step - accuracy: 0.2500 - loss: 2.4763[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1820 - loss: 2.6581
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 32ms/step - accuracy: 0.1820 - loss: 2.6580[32m [repeated 99x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m41s[0m 36ms/step - accuracy: 0.2535 - loss: 2.3638 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m37s[0m 33ms/step - accuracy: 0.2652 - loss: 2.2852
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 37ms/step - accuracy: 0.3536 - loss: 1.9402[32m [repeated 85x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m13s[0m 37ms/step - accuracy: 0.3005 - loss: 2.1228[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 24ms/step - accuracy: 0.2183 - loss: 2.3969
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 24ms/step - accuracy: 0.2182 - loss: 2.3963[32m [repeated 141x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m190/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 36ms/step - accuracy: 0.3320 - loss: 2.0248
[1m192/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 36ms/step - accuracy: 0.3319 - loss: 2.0250[32m [repeated 29x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 32ms/step - accuracy: 0.1821 - loss: 2.6564
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 32ms/step - accuracy: 0.1821 - loss: 2.6563
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 32ms/step - accuracy: 0.1821 - loss: 2.6563
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 35ms/step - accuracy: 0.3438 - loss: 2.1975 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.3003 - loss: 2.1230 
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m9s[0m 37ms/step - accuracy: 0.3003 - loss: 2.1230
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m  41/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 25ms/step - accuracy: 0.2218 - loss: 2.4020
[1m  44/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 24ms/step - accuracy: 0.2211 - loss: 2.4020
[1m  46/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 24ms/step - accuracy: 0.2207 - loss: 2.4019
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m172/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m14s[0m 36ms/step - accuracy: 0.3328 - loss: 2.0240[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 27ms/step - accuracy: 0.3120 - loss: 2.0772
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 27ms/step - accuracy: 0.3117 - loss: 2.0778
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 27ms/step - accuracy: 0.3114 - loss: 2.0783
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m459/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2316 - loss: 2.3653
[1m461/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2317 - loss: 2.3653[32m [repeated 26x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m470/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 33ms/step - accuracy: 0.2317 - loss: 2.3652[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 17/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m37s[0m 32ms/step - accuracy: 0.3057 - loss: 2.1178 - val_accuracy: 0.3149 - val_loss: 2.1691[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:22[0m 72ms/step - accuracy: 0.2500 - loss: 2.2417[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.3002 - loss: 2.1230
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m7s[0m 36ms/step - accuracy: 0.3002 - loss: 2.1230[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 31ms/step - accuracy: 0.1821 - loss: 2.6546[32m [repeated 49x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 204/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m25s[0m 26ms/step - accuracy: 0.3043 - loss: 2.0948[32m [repeated 103x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 21ms/step - accuracy: 0.2166 - loss: 2.3885
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m17s[0m 21ms/step - accuracy: 0.2166 - loss: 2.3885[32m [repeated 190x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m278/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.3302 - loss: 2.0285
[1m280/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m10s[0m 34ms/step - accuracy: 0.3302 - loss: 2.0286[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47[0m 93ms/step - accuracy: 0.2500 - loss: 2.4125
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3242 - loss: 2.0586 
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 40ms/step - accuracy: 0.3056 - loss: 2.2634 [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m282/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.3301 - loss: 2.0286 
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m408/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.3292 - loss: 2.0320
[1m409/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.3292 - loss: 2.0320[32m [repeated 46x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m425/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m5s[0m 33ms/step - accuracy: 0.3292 - loss: 2.0322[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m21s[0m 37ms/step - accuracy: 0.2327 - loss: 2.3635 - val_accuracy: 0.2819 - val_loss: 2.2100
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 18/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m36s[0m 31ms/step - accuracy: 0.2720 - loss: 2.2362 - val_accuracy: 0.3260 - val_loss: 2.1144[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:34[0m 82ms/step - accuracy: 0.2500 - loss: 2.5983
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m47s[0m 558ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 19ms/step - accuracy: 0.2955 - loss: 2.1135
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m7s[0m 19ms/step - accuracy: 0.2954 - loss: 2.1136[32m [repeated 71x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 4/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step  
[1m 7/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m12/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 36ms/step - accuracy: 0.3002 - loss: 2.1224[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m16/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m20/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m25/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m33/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m36/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m40/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 122/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 36ms/step - accuracy: 0.3474 - loss: 1.9579[32m [repeated 119x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 21ms/step - accuracy: 0.2162 - loss: 2.3896
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 21ms/step - accuracy: 0.2162 - loss: 2.3896[32m [repeated 214x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m44/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43[0m 89ms/step - accuracy: 0.3125 - loss: 2.4670
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.2465 - loss: 2.5977 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.2204 - loss: 2.6366
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m64/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m72/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[1m76/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m80/86[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=2697883)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 20ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 20ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 58ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m  6/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 11ms/step
[1m  9/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 13/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 17/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 21/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 24/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m 28/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 32/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 36/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.3333 - loss: 2.2277 
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 40/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 44/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 48/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  65/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 29ms/step - accuracy: 0.1845 - loss: 2.6647
[1m  67/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 29ms/step - accuracy: 0.1843 - loss: 2.6646
[1m  69/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 29ms/step - accuracy: 0.1839 - loss: 2.6647
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 54/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 58/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 62/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 66/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 69/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 73/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 77/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 81/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 85/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[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=2697883)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 89/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m 93/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m 97/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 14ms/step
[1m101/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m555/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3290 - loss: 2.0319
[1m557/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3290 - loss: 2.0319[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m105/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 14ms/step
[1m109/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m113/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[1m116/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.2164 - loss: 2.3886
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.2164 - loss: 2.3886
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.2164 - loss: 2.3886
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m119/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[1m123/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m126/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m131/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m569/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3290 - loss: 2.0319
[1m571/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3290 - loss: 2.0319
[1m572/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3289 - loss: 2.0319
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m134/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m139/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m143/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[1m148/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m152/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m574/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3289 - loss: 2.0319[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2697883)[0m 
[1m157/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 14ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 15ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:54:37. Total running time: 14min 16s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             853.616 │
│ time_total_s                 853.616 │
│ training_iteration                 1 │
│ val_accuracy                 0.28191 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:54:37. Total running time: 14min 16s
[36m(train_cnn_ray_tune pid=2697862)[0m Epoch 16/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 36ms/step - accuracy: 0.3082 - loss: 2.0809 - val_accuracy: 0.3583 - val_loss: 2.0915[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 22ms/step - accuracy: 0.2165 - loss: 2.3882
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 22ms/step - accuracy: 0.2165 - loss: 2.3882[32m [repeated 57x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 22ms/step - accuracy: 0.2165 - loss: 2.3881[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.1950 - loss: 2.4778 
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 24ms/step - accuracy: 0.1950 - loss: 2.4779
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m31s[0m 35ms/step - accuracy: 0.3530 - loss: 1.9326[32m [repeated 145x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 174/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 28ms/step - accuracy: 0.1775 - loss: 2.6629
[1m 176/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 28ms/step - accuracy: 0.1775 - loss: 2.6627[32m [repeated 251x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:32[0m 81ms/step - accuracy: 0.3750 - loss: 2.1709
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 178/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 28ms/step - accuracy: 0.1775 - loss: 2.6625
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 28ms/step - accuracy: 0.1774 - loss: 2.6623
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m27s[0m 28ms/step - accuracy: 0.1774 - loss: 2.6621
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m22s[0m 38ms/step - accuracy: 0.3289 - loss: 2.0319 - val_accuracy: 0.2964 - val_loss: 2.2132
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.2168 - loss: 2.3872
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.2168 - loss: 2.3872
[1m 873/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 21ms/step - accuracy: 0.2168 - loss: 2.3872
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m46s[0m 552ms/step
[1m 5/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step  
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:37[0m 85ms/step - accuracy: 0.5000 - loss: 1.8711
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m10/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m14/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 34ms/step - accuracy: 0.4410 - loss: 1.9927 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m39s[0m 34ms/step - accuracy: 0.4177 - loss: 1.9914
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m17/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m22/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m25/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m32/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m36/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m39/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 16ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 206/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m26s[0m 28ms/step - accuracy: 0.3072 - loss: 2.0602
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m26s[0m 28ms/step - accuracy: 0.3072 - loss: 2.0602
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m26s[0m 28ms/step - accuracy: 0.3072 - loss: 2.0603
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 15ms/step
[1m62/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 15ms/step
[1m71/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[1m77/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 15ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m576/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 33ms/step - accuracy: 0.3289 - loss: 2.0319
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 33ms/step - accuracy: 0.3289 - loss: 2.0319[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m80/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 15ms/step
[1m83/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 22ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 23ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 62ms/step
[1m  4/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m  8/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 11/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 15/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 18/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697817)[0m Epoch 14/27
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 22/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 26/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m47s[0m 41ms/step - accuracy: 0.3003 - loss: 2.1221 - val_accuracy: 0.3085 - val_loss: 2.1796
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 30/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 34/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 21ms/step - accuracy: 0.2172 - loss: 2.3858
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 21ms/step - accuracy: 0.2172 - loss: 2.3857[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 37/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 41/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m5s[0m 25ms/step - accuracy: 0.1946 - loss: 2.4799[32m [repeated 32x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2906 - loss: 2.1504 
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2906 - loss: 2.1504
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 45/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 49/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 52/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 56/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 60/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 63/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 67/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 70/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 74/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m26s[0m 22ms/step - accuracy: 0.2942 - loss: 2.1164 - val_accuracy: 0.2984 - val_loss: 2.1815
[36m(train_cnn_ray_tune pid=2697880)[0m Epoch 24/24
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m11s[0m 28ms/step - accuracy: 0.2983 - loss: 2.1144[32m [repeated 121x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[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=2697872)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 35ms/step - accuracy: 0.3559 - loss: 1.9238
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m25s[0m 35ms/step - accuracy: 0.3560 - loss: 1.9237[32m [repeated 227x across cluster][0m
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 78/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 82/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 86/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 90/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m 94/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m 98/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m102/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 16ms/step
[1m106/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m110/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 16ms/step
[1m113/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m117/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m121/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 16ms/step
[1m124/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m128/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 16ms/step
[1m132/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m136/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 16ms/step
[1m140/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m144/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 16ms/step
[1m148/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m151/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step
[1m155/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697872)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 16ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:54:45. Total running time: 14min 24s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             861.291 │
│ time_total_s                 861.291 │
│ training_iteration                 1 │
│ val_accuracy                 0.29641 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:54:45. Total running time: 14min 24s
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:24[0m 73ms/step - accuracy: 0.3750 - loss: 1.8247
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2852 - loss: 2.0218 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2602 - loss: 2.0857
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2981 - loss: 2.1150 
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2981 - loss: 2.1151
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2980 - loss: 2.1153
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2980 - loss: 2.1154
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.2980 - loss: 2.1154
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 28ms/step - accuracy: 0.2900 - loss: 2.1517
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m3s[0m 28ms/step - accuracy: 0.2900 - loss: 2.1517[32m [repeated 113x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 25ms/step - accuracy: 0.1943 - loss: 2.4818[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m20s[0m 35ms/step - accuracy: 0.3573 - loss: 1.9203[32m [repeated 148x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 28ms/step - accuracy: 0.1758 - loss: 2.6465
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m17s[0m 28ms/step - accuracy: 0.1758 - loss: 2.6464[32m [repeated 200x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m29s[0m 25ms/step - accuracy: 0.2177 - loss: 2.3842 - val_accuracy: 0.2857 - val_loss: 2.2255
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 22/26
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:40[0m 87ms/step - accuracy: 0.2500 - loss: 2.3563
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2845 
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 28ms/step - accuracy: 0.2900 - loss: 2.1518
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 28ms/step - accuracy: 0.2900 - loss: 2.1518
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 28ms/step - accuracy: 0.2900 - loss: 2.1519

Trial status: 9 TERMINATED | 11 RUNNING
Current time: 2025-11-07 12:54:52. Total running time: 14min 31s
Logical resource usage: 11.0/20 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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 16                  5                 0          0.000121681         24                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28        1            749.19          0.333929 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28        1            853.616         0.281914 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18        1            702.225         0.281517 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27        1            723.629         0.31348  │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000190495         29        1            679.655         0.323407 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28        1            861.291         0.296407 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43[0m 90ms/step - accuracy: 0.0000e+00 - loss: 2.8323
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1016 - loss: 2.5874     
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.1281 - loss: 2.5374
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 28ms/step - accuracy: 0.2974 - loss: 2.1175
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 28ms/step - accuracy: 0.2974 - loss: 2.1175[32m [repeated 106x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m2s[0m 26ms/step - accuracy: 0.3033 - loss: 2.1087[32m [repeated 73x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  40/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 23ms/step - accuracy: 0.1448 - loss: 2.5467
[1m  42/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 23ms/step - accuracy: 0.1454 - loss: 2.5469
[1m  44/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 23ms/step - accuracy: 0.1462 - loss: 2.5471
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 23ms/step - accuracy: 0.1500 - loss: 2.5469[32m [repeated 122x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 34ms/step - accuracy: 0.3578 - loss: 1.9210
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m14s[0m 34ms/step - accuracy: 0.3578 - loss: 1.9210[32m [repeated 184x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 28ms/step - accuracy: 0.1943 - loss: 2.4818 - val_accuracy: 0.2905 - val_loss: 2.2546
[36m(train_cnn_ray_tune pid=2697856)[0m Epoch 19/29
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.1761 - loss: 2.6441 
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.1761 - loss: 2.6441
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m37s[0m 32ms/step - accuracy: 0.2898 - loss: 2.1524 - val_accuracy: 0.3288 - val_loss: 2.0978
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m44s[0m 519ms/step
[1m 5/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step  
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 9/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 14ms/step
[1m13/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 14ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m23/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697835)[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=2697835)[0m 
[1m35/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m39/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m43/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 13ms/step
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[1m62/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m67/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step
[1m71/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m75/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 13ms/step
[1m79/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m83/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 18ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 18ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 51ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m  5/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 13ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 10/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 14/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.3114 - loss: 2.0582
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 28ms/step - accuracy: 0.3114 - loss: 2.0582[32m [repeated 100x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m6s[0m 27ms/step - accuracy: 0.1763 - loss: 2.6430[32m [repeated 41x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 19/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 24/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 29/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 34/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 39/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 43/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 47/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 52/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 57/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 62/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m18s[0m 22ms/step - accuracy: 0.1785 - loss: 2.5163[32m [repeated 92x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 20ms/step - accuracy: 0.2276 - loss: 2.3641
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 20ms/step - accuracy: 0.2276 - loss: 2.3641[32m [repeated 178x across cluster][0m
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 67/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[1m 72/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 20ms/step - accuracy: 0.2275 - loss: 2.3642
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 20ms/step - accuracy: 0.2275 - loss: 2.3643
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m13s[0m 20ms/step - accuracy: 0.2274 - loss: 2.3644
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 77/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m 82/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m Epoch 17/25
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 86/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m 92/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:23[0m 73ms/step - accuracy: 0.4375 - loss: 2.0474
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.3646 - loss: 2.0724 
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m 97/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 12ms/step
[1m102/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:30[0m 78ms/step - accuracy: 0.3750 - loss: 1.9388
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m108/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[1m113/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   3/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.3507 - loss: 2.0280 
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m117/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 12ms/step
[1m121/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m125/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m130/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m134/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697835)[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=2697835)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m139/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 12ms/step
[1m143/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m148/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step
[1m153/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697835)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 12ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 12ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:55:00. Total running time: 14min 39s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             876.218 │
│ time_total_s                 876.218 │
│ training_iteration                 1 │
│ val_accuracy                 0.32877 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:55:00. Total running time: 14min 39s
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m12s[0m 20ms/step - accuracy: 0.2268 - loss: 2.3653
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 20ms/step - accuracy: 0.2268 - loss: 2.3653
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m12s[0m 20ms/step - accuracy: 0.2267 - loss: 2.3654
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.3576 - loss: 1.9217 
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 34ms/step - accuracy: 0.3576 - loss: 1.9217[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m33s[0m 29ms/step - accuracy: 0.3036 - loss: 2.1084 - val_accuracy: 0.3208 - val_loss: 2.1924[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2461 - loss: 2.3244 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2415 - loss: 2.3482
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 33ms/step - accuracy: 0.3577 - loss: 1.9222
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m4s[0m 33ms/step - accuracy: 0.3577 - loss: 1.9222[32m [repeated 131x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 27ms/step - accuracy: 0.1769 - loss: 2.6413[32m [repeated 76x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 27ms/step - accuracy: 0.1769 - loss: 2.6412
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m1s[0m 27ms/step - accuracy: 0.1769 - loss: 2.6412
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 27ms/step - accuracy: 0.1769 - loss: 2.6412
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m12s[0m 31ms/step - accuracy: 0.3072 - loss: 2.0994[32m [repeated 65x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m14s[0m 22ms/step - accuracy: 0.1845 - loss: 2.5074
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m13s[0m 22ms/step - accuracy: 0.1846 - loss: 2.5073[32m [repeated 170x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 19/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:41[0m 88ms/step - accuracy: 0.2500 - loss: 2.1446
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.2260 - loss: 2.3667 
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.2260 - loss: 2.3668
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m32s[0m 28ms/step - accuracy: 0.2804 - loss: 2.2031 - val_accuracy: 0.3216 - val_loss: 2.1086
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 31ms/step - accuracy: 0.3070 - loss: 2.0992
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m10s[0m 31ms/step - accuracy: 0.3070 - loss: 2.0992
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m9s[0m 31ms/step - accuracy: 0.3070 - loss: 2.0992 
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.1868 - loss: 2.5031 
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 22ms/step - accuracy: 0.1869 - loss: 2.5030
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 21ms/step - accuracy: 0.2906 - loss: 2.1322 - val_accuracy: 0.3081 - val_loss: 2.2002
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 350ms/step
[1m10/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step   
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m19/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m27/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m34/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:28[0m 77ms/step - accuracy: 0.2500 - loss: 2.4427
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m22s[0m 20ms/step - accuracy: 0.2214 - loss: 2.4960 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 19ms/step - accuracy: 0.2189 - loss: 2.5631
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 19ms/step - accuracy: 0.2253 - loss: 2.3683
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m3s[0m 19ms/step - accuracy: 0.2253 - loss: 2.3683[32m [repeated 110x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m8s[0m 21ms/step - accuracy: 0.1873 - loss: 2.5023[32m [repeated 78x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m66/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 7ms/step
[1m74/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m82/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.2254 - loss: 2.3680
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.2254 - loss: 2.3681
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m6s[0m 20ms/step - accuracy: 0.2254 - loss: 2.3681
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m16s[0m 21ms/step - accuracy: 0.2743 - loss: 2.2205[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  37/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 19ms/step - accuracy: 0.1945 - loss: 2.6460
[1m  40/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 19ms/step - accuracy: 0.1936 - loss: 2.6452[32m [repeated 145x across cluster][0m
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 39ms/step
[1m  9/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step 
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 17/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m Epoch 17/17
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 25/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 33/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 41/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 49/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697880)[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=2697880)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 57/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 64/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 72/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 80/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m 89/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 97/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m105/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 7ms/step
[1m114/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m122/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 7ms/step
[1m131/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m138/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m Epoch 17/27
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m146/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 7ms/step
[1m155/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:19[0m 69ms/step - accuracy: 0.1250 - loss: 2.5202
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2487 - loss: 2.2545 
[36m(train_cnn_ray_tune pid=2697880)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:55:10. Total running time: 14min 49s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             886.683 │
│ time_total_s                 886.683 │
│ training_iteration                 1 │
│ val_accuracy                 0.30812 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:55:10. Total running time: 14min 49s
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 18ms/step - accuracy: 0.2249 - loss: 2.3685
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 18ms/step - accuracy: 0.2249 - loss: 2.3685
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 18ms/step - accuracy: 0.2249 - loss: 2.3685
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m21s[0m 19ms/step - accuracy: 0.2003 - loss: 2.6378
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 19ms/step - accuracy: 0.1995 - loss: 2.6405
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 19ms/step - accuracy: 0.1984 - loss: 2.6427
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 471ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 6/86[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 11ms/step  
[1m11/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m16/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m26/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m36/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m46/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m70/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m75/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m42s[0m 36ms/step - accuracy: 0.3578 - loss: 1.9224 - val_accuracy: 0.3264 - val_loss: 2.1216[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m80/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m84/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 12ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 16ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 17ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 42ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m  6/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 12/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 20ms/step - accuracy: 0.1888 - loss: 2.5000
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 20ms/step - accuracy: 0.1888 - loss: 2.4999[32m [repeated 88x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.3013 - loss: 2.1017[32m [repeated 42x across cluster][0m
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 17/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 23/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 28/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 34/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 40/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 45/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 51/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 10ms/step
[1m 57/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 63/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m 69/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 75/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 10ms/step
[1m 81/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 9ms/step 
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m10s[0m 21ms/step - accuracy: 0.2954 - loss: 2.1074[32m [repeated 61x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 18ms/step - accuracy: 0.1799 - loss: 2.6242
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m15s[0m 18ms/step - accuracy: 0.1798 - loss: 2.6242[32m [repeated 162x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.2954 - loss: 2.1074 
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m9s[0m 21ms/step - accuracy: 0.2954 - loss: 2.1073
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 87/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[1m 93/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m 99/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m105/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m111/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m117/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m123/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m129/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m135/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m141/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 9ms/step
[1m147/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m153/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2697836)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 10ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:55:15. Total running time: 14min 54s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             891.395 │
│ time_total_s                 891.395 │
│ training_iteration                 1 │
│ val_accuracy                 0.32638 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:55:15. Total running time: 14min 54s
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 18ms/step - accuracy: 0.1797 - loss: 2.6237
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 18ms/step - accuracy: 0.1797 - loss: 2.6237
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m13s[0m 18ms/step - accuracy: 0.1797 - loss: 2.6236
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 23/26
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.3750 - loss: 2.1851
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 11ms/step - accuracy: 0.2457 - loss: 2.3467 
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.3009 - loss: 2.1024
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.3009 - loss: 2.1023
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m9s[0m 20ms/step - accuracy: 0.3010 - loss: 2.1022
[36m(train_cnn_ray_tune pid=2697817)[0m Epoch 15/27
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.5000 - loss: 1.7225
[1m   4/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m20s[0m 18ms/step - accuracy: 0.4453 - loss: 1.8607 
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m24s[0m 21ms/step - accuracy: 0.1891 - loss: 2.4992 - val_accuracy: 0.2742 - val_loss: 2.2578[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 16ms/step - accuracy: 0.2770 - loss: 2.2094
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 16ms/step - accuracy: 0.2770 - loss: 2.2094[32m [repeated 146x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m2s[0m 19ms/step - accuracy: 0.2967 - loss: 2.1063[32m [repeated 58x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 16ms/step - accuracy: 0.3200 - loss: 2.0792[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 181/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 13ms/step - accuracy: 0.1839 - loss: 2.5100
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m12s[0m 13ms/step - accuracy: 0.1842 - loss: 2.5093[32m [repeated 111x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 16ms/step - accuracy: 0.1795 - loss: 2.6230
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 16ms/step - accuracy: 0.1795 - loss: 2.6230
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m7s[0m 16ms/step - accuracy: 0.1795 - loss: 2.6230
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 53ms/step - accuracy: 0.5000 - loss: 1.8032
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 19/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.4448 - loss: 1.8537 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.4165 - loss: 1.9004
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1875 - loss: 2.6204
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 13ms/step - accuracy: 0.1844 - loss: 2.5986 
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:04[0m 56ms/step - accuracy: 0.2500 - loss: 2.3153
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 12ms/step - accuracy: 0.2884 - loss: 2.2159 

Trial status: 12 TERMINATED | 8 RUNNING
Current time: 2025-11-07 12:55:22. Total running time: 15min 1s
Logical resource usage: 8.0/20 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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23        1            891.395         0.326385 │
│ trial_8aa9a    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28        1            749.19          0.333929 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28        1            853.616         0.281914 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18        1            702.225         0.281517 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27        1            723.629         0.31348  │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   16                 16                  5                 0          0.000121681         24        1            886.683         0.30812  │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000190495         29        1            679.655         0.323407 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16        1            876.218         0.328767 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28        1            861.291         0.296407 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 13ms/step - accuracy: 0.2156 - loss: 2.2088 
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m23s[0m 20ms/step - accuracy: 0.2970 - loss: 2.1064 - val_accuracy: 0.3055 - val_loss: 2.1798[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 15ms/step - accuracy: 0.1804 - loss: 2.6211
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 15ms/step - accuracy: 0.1804 - loss: 2.6211[32m [repeated 172x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m4s[0m 15ms/step - accuracy: 0.3186 - loss: 2.0479[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m10s[0m 16ms/step - accuracy: 0.3174 - loss: 2.0823[32m [repeated 17x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.2910 - loss: 2.1721
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m11s[0m 12ms/step - accuracy: 0.2908 - loss: 2.1728[32m [repeated 114x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.2307 - loss: 2.3433
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.2307 - loss: 2.3434
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.2307 - loss: 2.3435[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.2860 - loss: 2.1867 
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.2858 - loss: 2.1870
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 55ms/step - accuracy: 0.1875 - loss: 2.1889
[36m(train_cnn_ray_tune pid=2697885)[0m Epoch 18/25[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 14ms/step - accuracy: 0.2961 - loss: 2.1024
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 14ms/step - accuracy: 0.2961 - loss: 2.1025
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 14ms/step - accuracy: 0.2961 - loss: 2.1025
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.1875 - loss: 2.2735
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 12ms/step - accuracy: 0.2299 - loss: 2.3456 - val_accuracy: 0.2950 - val_loss: 2.2264[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 402ms/step
[1m 9/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step   
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m17/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m25/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m33/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m41/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 7ms/step
[1m65/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 7ms/step
[1m81/86[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.2829 - loss: 2.1920
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m6s[0m 12ms/step - accuracy: 0.2829 - loss: 2.1920[32m [repeated 182x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.1960 - loss: 2.4789[32m [repeated 51x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 11ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697871)[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=2697871)[0m   _log_deprecation_warning([32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 38ms/step
[1m  9/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step 
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   5/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 15ms/step - accuracy: 0.2994 - loss: 2.0715 
[1m   9/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m16s[0m 14ms/step - accuracy: 0.2939 - loss: 2.0912
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 17/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 24/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 31/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 39/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 14ms/step - accuracy: 0.2996 - loss: 2.0864[32m [repeated 18x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 13ms/step - accuracy: 0.3037 - loss: 2.0827
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 13ms/step - accuracy: 0.3040 - loss: 2.0794[32m [repeated 60x across cluster][0m
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 47/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 55/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 64/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 71/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 79/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m 87/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 7ms/step
[1m 95/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m103/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 7ms/step
[1m111/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m119/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 7ms/step
[1m127/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m135/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 7ms/step
[1m143/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 7ms/step
[36m(train_cnn_ray_tune pid=2697871)[0m 
[1m151/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 7ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:55:30. Total running time: 15min 9s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s              906.48 │
│ time_total_s                  906.48 │
│ training_iteration                 1 │
│ val_accuracy                 0.23486 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:55:30. Total running time: 15min 9s
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.2964 - loss: 2.1026 
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.2964 - loss: 2.1026[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m Epoch 18/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:05[0m 56ms/step - accuracy: 0.1875 - loss: 2.5430
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 11ms/step - accuracy: 0.1493 - loss: 2.5144 
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:02[0m 54ms/step - accuracy: 0.3750 - loss: 1.9679
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 13ms/step - accuracy: 0.1961 - loss: 2.4783 - val_accuracy: 0.2650 - val_loss: 2.2503[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.2324 - loss: 2.3315
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.2324 - loss: 2.3316
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.2323 - loss: 2.3317
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 11ms/step - accuracy: 0.2815 - loss: 2.1928
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 11ms/step - accuracy: 0.2815 - loss: 2.1928[32m [repeated 206x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m1s[0m 15ms/step - accuracy: 0.3149 - loss: 2.0870[32m [repeated 62x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.3171 - loss: 2.0291[32m [repeated 9x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.1915 - loss: 2.4569
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.1918 - loss: 2.4573[32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 9ms/step - accuracy: 0.2318 - loss: 2.3330 
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 9ms/step - accuracy: 0.2317 - loss: 2.3331
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 9ms/step - accuracy: 0.2317 - loss: 2.3332
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2317 - loss: 2.3332
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2317 - loss: 2.3333
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2317 - loss: 2.3334
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2316 - loss: 2.3335
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2316 - loss: 2.3335
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2316 - loss: 2.3336
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2315 - loss: 2.3337
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2315 - loss: 2.3338
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2315 - loss: 2.3339
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2315 - loss: 2.3341
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2314 - loss: 2.3342
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2314 - loss: 2.3343
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2314 - loss: 2.3344
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2313 - loss: 2.3345
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2313 - loss: 2.3346
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2313 - loss: 2.3347
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2313 - loss: 2.3348
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2312 - loss: 2.3349
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2312 - loss: 2.3350
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2312 - loss: 2.3351
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2311 - loss: 2.3352
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2311 - loss: 2.3353
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2311 - loss: 2.3354
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.2500 - loss: 2.0628
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 20/27[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 49ms/step - accuracy: 0.3125 - loss: 2.0316
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 11ms/step - accuracy: 0.3266 - loss: 2.0054[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2305 - loss: 2.3375
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 13ms/step - accuracy: 0.3282 - loss: 2.0632 - val_accuracy: 0.3121 - val_loss: 2.1884[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.2779 - loss: 2.1880 
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.2777 - loss: 2.1887
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2305 - loss: 2.3376
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 172/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.3252 - loss: 2.0164
[1m 177/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.3253 - loss: 2.0170
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m10s[0m 11ms/step - accuracy: 0.3253 - loss: 2.0176
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.2772 - loss: 2.1927
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m8s[0m 10ms/step - accuracy: 0.2772 - loss: 2.1929[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m4s[0m 10ms/step - accuracy: 0.1973 - loss: 2.4669[32m [repeated 30x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m4s[0m 10ms/step - accuracy: 0.1973 - loss: 2.4670
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m4s[0m 10ms/step - accuracy: 0.1973 - loss: 2.4670
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 10ms/step - accuracy: 0.1973 - loss: 2.4671
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.3240 - loss: 2.0528[32m [repeated 6x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.3044 - loss: 2.0675
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 12ms/step - accuracy: 0.3043 - loss: 2.0694[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.1957 - loss: 2.4625 
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.1958 - loss: 2.4625
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2305 - loss: 2.3375
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2305 - loss: 2.3376[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 10ms/step - accuracy: 0.2304 - loss: 2.3376 - val_accuracy: 0.2936 - val_loss: 2.2224
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.1973 - loss: 2.4676
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.1973 - loss: 2.4676
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.1973 - loss: 2.4676
[36m(train_cnn_ray_tune pid=2697829)[0m Epoch 25/26[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:03[0m 55ms/step - accuracy: 0.1875 - loss: 2.3438
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m10s[0m 9ms/step - accuracy: 0.2159 - loss: 2.2850  [32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 14ms/step - accuracy: 0.2997 - loss: 2.0994 - val_accuracy: 0.3105 - val_loss: 2.2046
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.3082 - loss: 2.0817 
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.3083 - loss: 2.0818[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.2798 - loss: 2.1896
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m4s[0m 11ms/step - accuracy: 0.2798 - loss: 2.1896[32m [repeated 204x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m8s[0m 12ms/step - accuracy: 0.3086 - loss: 2.0840[32m [repeated 25x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 10ms/step - accuracy: 0.2399 - loss: 2.3279
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 10ms/step - accuracy: 0.2398 - loss: 2.3280
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m7s[0m 9ms/step - accuracy: 0.2397 - loss: 2.3282 
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 14ms/step - accuracy: 0.3270 - loss: 2.0534[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.3080 - loss: 2.0816
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.3081 - loss: 2.0816[32m [repeated 47x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m16s[0m 13ms/step - accuracy: 0.3233 - loss: 2.0254 - val_accuracy: 0.3536 - val_loss: 2.0896
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.2380 - loss: 2.3322
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.2379 - loss: 2.3324[32m [repeated 15x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m5s[0m 9ms/step - accuracy: 0.2378 - loss: 2.3327
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.3125 - loss: 2.1233
[36m(train_cnn_ray_tune pid=2697856)[0m Epoch 22/29[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2367 - loss: 2.3344
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2367 - loss: 2.3344
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m3s[0m 9ms/step - accuracy: 0.2366 - loss: 2.3345
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.3750 - loss: 1.8907
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 12ms/step - accuracy: 0.3599 - loss: 1.9199
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 11ms/step - accuracy: 0.2063 - loss: 2.4532 
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m9s[0m 11ms/step - accuracy: 0.2061 - loss: 2.4534
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.3084 - loss: 2.0844
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.3084 - loss: 2.0844
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m3s[0m 12ms/step - accuracy: 0.3084 - loss: 2.0844
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 14ms/step - accuracy: 0.3241 - loss: 2.0599
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m2s[0m 14ms/step - accuracy: 0.3240 - loss: 2.0599[32m [repeated 164x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.3263 - loss: 2.0401[32m [repeated 27x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 9ms/step - accuracy: 0.2355 - loss: 2.3360
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.3400 - loss: 2.0132[32m [repeated 11x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m10s[0m 12ms/step - accuracy: 0.3395 - loss: 2.0131
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m9s[0m 12ms/step - accuracy: 0.3394 - loss: 2.0130 [32m [repeated 55x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 12ms/step - accuracy: 0.1976 - loss: 2.4677 - val_accuracy: 0.2819 - val_loss: 2.2442
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2350 - loss: 2.3364
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2349 - loss: 2.3365[32m [repeated 44x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 12ms/step - accuracy: 0.2812 - loss: 2.1860 - val_accuracy: 0.3288 - val_loss: 2.1133
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m59s[0m 52ms/step - accuracy: 0.1875 - loss: 2.2550
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.2393 - loss: 2.2437
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 9ms/step - accuracy: 0.2345 - loss: 2.3369
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:01[0m 54ms/step - accuracy: 0.1875 - loss: 2.1915
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   6/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m11s[0m 10ms/step - accuracy: 0.2946 - loss: 2.0974 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m12s[0m 11ms/step - accuracy: 0.2976 - loss: 2.0935
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 21/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 11ms/step - accuracy: 0.2345 - loss: 2.3369 - val_accuracy: 0.2962 - val_loss: 2.2235
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 7ms/step - accuracy: 0.2953 - loss: 2.2630

Trial status: 13 TERMINATED | 7 RUNNING
Current time: 2025-11-07 12:55:53. Total running time: 15min 31s
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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25                                              │
│ trial_8aa9a    RUNNING              3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    RUNNING              2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23        1            891.395         0.326385 │
│ trial_8aa9a    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28        1            749.19          0.333929 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28        1            853.616         0.281914 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18        1            702.225         0.281517 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27        1            723.629         0.31348  │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   16                 16                  5                 0          0.000121681         24        1            886.683         0.30812  │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000190495         29        1            679.655         0.323407 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16        1            876.218         0.328767 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17        1            906.48          0.234862 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28        1            861.291         0.296407 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.3008 - loss: 2.0815 
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.3009 - loss: 2.0816
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 151/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 7ms/step - accuracy: 0.2432 - loss: 2.3007
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 7ms/step - accuracy: 0.2428 - loss: 2.3013
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m7s[0m 7ms/step - accuracy: 0.2425 - loss: 2.3017
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.2888 - loss: 2.1533 
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 10ms/step - accuracy: 0.2886 - loss: 2.1543
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.1997 - loss: 2.4652
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.1996 - loss: 2.4653
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m5s[0m 10ms/step - accuracy: 0.1996 - loss: 2.4654
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.1993 - loss: 2.4675
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.1993 - loss: 2.4675[32m [repeated 138x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.1993 - loss: 2.4675[32m [repeated 24x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 410ms/step
[1m 9/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step   
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m18/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m27/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m35/86[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m60/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 6ms/step
[1m77/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.1993 - loss: 2.4674
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.1993 - loss: 2.4674
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 10ms/step - accuracy: 0.1993 - loss: 2.4674
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m15s[0m 13ms/step - accuracy: 0.3846 - loss: 1.9825
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 14ms/step - accuracy: 0.3435 - loss: 2.0242
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 14ms/step - accuracy: 0.3429 - loss: 2.0245[32m [repeated 34x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2355 - loss: 2.3145
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2353 - loss: 2.3149[32m [repeated 64x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 10ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 11ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 13ms/step - accuracy: 0.3084 - loss: 2.0837 - val_accuracy: 0.2966 - val_loss: 2.2085[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m51s[0m 45ms/step - accuracy: 0.4375 - loss: 1.8011
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 8ms/step - accuracy: 0.3343 - loss: 2.2319  
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 38ms/step
[1m  9/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step 
[36m(train_cnn_ray_tune pid=2697885)[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=2697885)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 13ms/step - accuracy: 0.3364 - loss: 2.0305
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 17/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m 27/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 35/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m 43/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 52/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m 61/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.1994 - loss: 2.4669
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.1994 - loss: 2.4668
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m1s[0m 10ms/step - accuracy: 0.1995 - loss: 2.4668
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2346 - loss: 2.3164[32m [repeated 12x across cluster][0m
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 69/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m 77/158[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m 86/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 6ms/step
[1m 96/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m105/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 6ms/step
[1m114/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m122/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 6ms/step
[1m131/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 50ms/step - accuracy: 0.3750 - loss: 2.1336
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m140/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m149/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 6ms/step
[1m157/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 6ms/step
[36m(train_cnn_ray_tune pid=2697885)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 6ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:55:56. Total running time: 15min 35s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             932.309 │
│ time_total_s                 932.309 │
│ training_iteration                 1 │
│ val_accuracy                 0.29661 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:55:56. Total running time: 15min 35s
[36m(train_cnn_ray_tune pid=2697817)[0m Epoch 17/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step - accuracy: 0.1997 - loss: 2.4662
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step - accuracy: 0.1997 - loss: 2.4661
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 10ms/step - accuracy: 0.1997 - loss: 2.4661
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.1997 - loss: 2.4660
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.1997 - loss: 2.4660
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 10ms/step - accuracy: 0.1998 - loss: 2.4659
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 13ms/step - accuracy: 0.3298 - loss: 2.0368
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m11s[0m 13ms/step - accuracy: 0.3295 - loss: 2.0374
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2877 - loss: 2.1692 
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 9ms/step - accuracy: 0.2877 - loss: 2.1692
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.3290 - loss: 2.0388 
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.3133 - loss: 2.0660
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m3s[0m 10ms/step - accuracy: 0.3134 - loss: 2.0659[32m [repeated 112x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m9s[0m 13ms/step - accuracy: 0.3290 - loss: 2.0387[32m [repeated 22x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:00[0m 52ms/step - accuracy: 0.2500 - loss: 2.4013
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   7/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.2045 - loss: 2.5487   
[1m  13/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.2036 - loss: 2.5395
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.3289 - loss: 2.0388
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m10s[0m 13ms/step - accuracy: 0.3289 - loss: 2.0388[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 409ms/step
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2877 - loss: 2.1694
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 9ms/step - accuracy: 0.2877 - loss: 2.1694[32m [repeated 77x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m11/86[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 6ms/step   
[1m21/86[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m15s[0m 13ms/step - accuracy: 0.3323 - loss: 2.0132 - val_accuracy: 0.3540 - val_loss: 2.0855[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m31/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m42/86[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 5ms/step
[1m63/86[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 5ms/step
[1m73/86[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m83/86[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 175/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m8s[0m 9ms/step - accuracy: 0.1939 - loss: 2.5082[32m [repeated 10x across cluster][0m
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 10ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 34ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 11/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step 
[1m 23/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 34/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m 45/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 56/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m 68/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m 79/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 5ms/step
[1m 90/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m101/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 5ms/step
[1m112/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m125/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 5ms/step
[1m137/158[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 5ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m Epoch 23/29
[36m(train_cnn_ray_tune pid=2697862)[0m 
[1m149/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 5ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 5ms/step

[36m(train_cnn_ray_tune pid=2697862)[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=2697862)[0m   _log_deprecation_warning(
Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:56:02. Total running time: 15min 41s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             938.011 │
│ time_total_s                 938.011 │
│ training_iteration                 1 │
│ val_accuracy                 0.35398 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:56:02. Total running time: 15min 41s
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 10ms/step - accuracy: 0.2877 - loss: 2.1693 - val_accuracy: 0.3274 - val_loss: 2.1016
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 23/27
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m50s[0m 44ms/step - accuracy: 0.3125 - loss: 2.6795
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8s[0m 7ms/step - accuracy: 0.2659 - loss: 2.2818  
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 291ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  43/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1875 - loss: 2.5664 
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 9ms/step - accuracy: 0.1868 - loss: 2.5648
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 35ms/step
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.3285 - loss: 2.0409
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m2s[0m 12ms/step - accuracy: 0.3285 - loss: 2.0409[32m [repeated 69x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m4s[0m 12ms/step - accuracy: 0.3286 - loss: 2.0408[32m [repeated 6x across cluster][0m

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:56:04. Total running time: 15min 43s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             940.536 │
│ time_total_s                 940.536 │
│ training_iteration                 1 │
│ val_accuracy                 0.30494 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:56:04. Total running time: 15min 43s
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2749 - loss: 2.1832
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2751 - loss: 2.1831[32m [repeated 101x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m16/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step   
[1m32/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 11ms/step - accuracy: 0.3165 - loss: 2.0622 - val_accuracy: 0.3006 - val_loss: 2.1842
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step[32m [repeated 4x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m6s[0m 8ms/step - accuracy: 0.2734 - loss: 2.1835[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m 15/158[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step 
[1m 30/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 4ms/step
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2697829)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m11s[0m 9ms/step - accuracy: 0.2290 - loss: 2.3274 - val_accuracy: 0.3049 - val_loss: 2.2193
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 22/27
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 46ms/step - accuracy: 0.4375 - loss: 1.7446
[1m   8/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m9s[0m 8ms/step - accuracy: 0.3932 - loss: 1.8484  
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m14s[0m 12ms/step - accuracy: 0.3282 - loss: 2.0416 - val_accuracy: 0.2990 - val_loss: 2.2043
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 305ms/step
[1m16/86[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step   
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step
[36m(train_cnn_ray_tune pid=2697817)[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=2697817)[0m   _log_deprecation_warning([32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m10s[0m 8ms/step - accuracy: 0.2014 - loss: 2.4605 - val_accuracy: 0.2690 - val_loss: 2.2501
[36m(train_cnn_ray_tune pid=2697856)[0m Epoch 24/29
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m 16/158[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step 
[1m 31/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m43s[0m 38ms/step - accuracy: 0.0625 - loss: 3.0054
[1m  10/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m6s[0m 6ms/step - accuracy: 0.1320 - loss: 2.6323  
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.3282 - loss: 2.0415
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 11ms/step - accuracy: 0.3282 - loss: 2.0416[32m [repeated 16x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m1s[0m 11ms/step - accuracy: 0.3284 - loss: 2.0411[32m [repeated 10x across cluster][0m

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:56:09. Total running time: 15min 48s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             945.623 │
│ time_total_s                 945.623 │
│ training_iteration                 1 │
│ val_accuracy                 0.29899 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:56:09. Total running time: 15min 48s
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 6ms/step - accuracy: 0.3278 - loss: 2.0244
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 6ms/step - accuracy: 0.3278 - loss: 2.0244[32m [repeated 125x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 6ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m36s[0m 32ms/step - accuracy: 0.2500 - loss: 2.9325
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m  12/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2831 - loss: 2.3546  
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2864 - loss: 2.2547
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2889 - loss: 2.1935[32m [repeated 14x across cluster][0m
[36m(train_cnn_ray_tune pid=2697817)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step[32m [repeated 5x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m8s[0m 7ms/step - accuracy: 0.3280 - loss: 2.0243 - val_accuracy: 0.3026 - val_loss: 2.2153[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m Epoch 23/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 5ms/step - accuracy: 0.2932 - loss: 2.1373
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 5ms/step - accuracy: 0.2933 - loss: 2.1373[32m [repeated 117x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.3750 - loss: 2.1730
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2163 - loss: 2.4642  
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.4375 - loss: 1.9217
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m  11/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.3430 - loss: 2.0709  
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.3417 - loss: 2.0540
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m2s[0m 5ms/step - accuracy: 0.3428 - loss: 2.0024[32m [repeated 13x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m38s[0m 33ms/step - accuracy: 0.3125 - loss: 2.0868
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m  12/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m5s[0m 5ms/step - accuracy: 0.2684 - loss: 2.1684  
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m17s[0m 209ms/step
[36m(train_cnn_ray_tune pid=2697864)[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=2697864)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m25/86[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step   
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m76/86[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m2s[0m 5ms/step - accuracy: 0.2033 - loss: 2.4413
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m2s[0m 5ms/step - accuracy: 0.2033 - loss: 2.4413
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m2s[0m 5ms/step - accuracy: 0.2033 - loss: 2.4412
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 24ms/step
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 26/158[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step 
[1m 52/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m 79/158[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step
[1m106/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step
[1m132/158[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m6s[0m 6ms/step - accuracy: 0.3413 - loss: 2.0062 - val_accuracy: 0.3208 - val_loss: 2.2007[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 25/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:56:19. Total running time: 15min 58s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             955.282 │
│ time_total_s                 955.282 │
│ training_iteration                 1 │
│ val_accuracy                 0.32083 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:56:19. Total running time: 15min 58s
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.3019 - loss: 2.1345
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m1s[0m 4ms/step - accuracy: 0.3018 - loss: 2.1345[32m [repeated 102x across cluster][0m
[36m(train_cnn_ray_tune pid=2697864)[0m 
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 5ms/step - accuracy: 0.3413 - loss: 2.0062
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step - accuracy: 0.3012 - loss: 2.1356
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 4ms/step - accuracy: 0.1919 - loss: 2.3982  
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 4ms/step - accuracy: 0.1958 - loss: 2.3992
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2500 - loss: 2.1197
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 28ms/step - accuracy: 0.4375 - loss: 1.7082
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m  15/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 4ms/step - accuracy: 0.3245 - loss: 2.0919  

Trial status: 18 TERMINATED | 2 RUNNING
Current time: 2025-11-07 12:56:23. Total running time: 16min 1s
Logical resource usage: 2.0/20 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_8aa9a    RUNNING              2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27                                              │
│ trial_8aa9a    RUNNING              3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29                                              │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23        1            891.395         0.326385 │
│ trial_8aa9a    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28        1            749.19          0.333929 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27        1            955.282         0.320826 │
│ trial_8aa9a    TERMINATED           3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27        1            945.623         0.298987 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28        1            853.616         0.281914 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18        1            702.225         0.281517 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27        1            723.629         0.31348  │
│ trial_8aa9a    TERMINATED           3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25        1            932.309         0.296605 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   16                 16                  5                 0          0.000121681         24        1            886.683         0.30812  │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000190495         29        1            679.655         0.323407 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27        1            938.011         0.353981 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16        1            876.218         0.328767 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26        1            940.536         0.304943 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17        1            906.48          0.234862 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28        1            861.291         0.296407 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 5ms/step - accuracy: 0.3012 - loss: 2.1356 - val_accuracy: 0.3365 - val_loss: 2.1016[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 26/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.3023 - loss: 2.1287
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.3023 - loss: 2.1286[32m [repeated 81x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[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=2697865)[0m   _log_deprecation_warning(
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step - accuracy: 0.3023 - loss: 2.1271[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 28ms/step - accuracy: 0.2500 - loss: 2.6408
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 4ms/step - accuracy: 0.2096 - loss: 2.5439  
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.4375 - loss: 1.8006
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m  14/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 4ms/step - accuracy: 0.3404 - loss: 2.0657  
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m4s[0m 4ms/step - accuracy: 0.3336 - loss: 2.0644
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 4ms/step - accuracy: 0.3023 - loss: 2.1270 - val_accuracy: 0.3371 - val_loss: 2.0926[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m Epoch 27/27[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.3051 - loss: 2.1139
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 4ms/step - accuracy: 0.3050 - loss: 2.1139[32m [repeated 80x across cluster][0m
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 4ms/step - accuracy: 0.3049 - loss: 2.1142[32m [repeated 3x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.1991
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.3175 - loss: 2.1918  
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m14s[0m 166ms/step
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m29/86[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step   
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2697865)[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=2697865)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 19ms/step
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 32/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step 
[1m 64/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m 95/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step
[1m126/158[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2697865)[0m 
[1m157/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:56:33. Total running time: 16min 11s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s              968.68 │
│ time_total_s                  968.68 │
│ training_iteration                 1 │
│ val_accuracy                 0.34862 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:56:33. Total running time: 16min 11s
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m5s[0m 5ms/step - accuracy: 0.2091 - loss: 2.4312 - val_accuracy: 0.2762 - val_loss: 2.2292[32m [repeated 2x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m Epoch 28/29
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 3ms/step - accuracy: 0.2182 - loss: 2.3983
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 3ms/step - accuracy: 0.2181 - loss: 2.3985[32m [repeated 50x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m Epoch 29/29
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.6244
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  16/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.1878 - loss: 2.4822  
[1m  32/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.1918 - loss: 2.4565
2025-11-07 12:56:41,467	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_M/case_M_CAPTURE24_acc_17_classes/CAPTURE24_hyperparameters_tuning' in 0.0051s.
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 179/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.1990 - loss: 2.4318
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.1997 - loss: 2.4296
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.2000 - loss: 2.4282
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step - accuracy: 0.2178 - loss: 2.3991
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 4ms/step - accuracy: 0.2177 - loss: 2.3993 - val_accuracy: 0.2728 - val_loss: 2.2345
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step - accuracy: 0.2091 - loss: 2.4086
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m4s[0m 4ms/step - accuracy: 0.2091 - loss: 2.4086 - val_accuracy: 0.2722 - val_loss: 2.2354
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m13s[0m 160ms/step
[1m33/86[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step   
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step - accuracy: 0.2090 - loss: 2.4088
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 3ms/step - accuracy: 0.2090 - loss: 2.4087[32m [repeated 33x across cluster][0m
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m68/86[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 3ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 25ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m 35/158[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 2ms/step 
[1m 71/158[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m107/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 1ms/step
[1m143/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step

Trial trial_8aa9a finished iteration 1 at 2025-11-07 12:56:41. Total running time: 16min 20s
╭──────────────────────────────────────╮
│ Trial trial_8aa9a result             │
├──────────────────────────────────────┤
│ checkpoint_dir_name                  │
│ time_this_iter_s             977.154 │
│ time_total_s                 977.154 │
│ training_iteration                 1 │
│ val_accuracy                 0.27219 │
╰──────────────────────────────────────╯

Trial trial_8aa9a completed after 1 iterations at 2025-11-07 12:56:41. Total running time: 16min 20s

Trial status: 20 TERMINATED
Current time: 2025-11-07 12:56:41. Total running time: 16min 20s
Logical resource usage: 1.0/20 CPUs, 0/1 GPUs (0.0/1.0 accelerator_type:G)
I0000 00:00:1762516601.593874 2696240 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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=2697856)[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=2697856)[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_8aa9a    TERMINATED           2   adam            tanh                                   32                 32                  3                 0          0.00010593          27        1            508.556         0.312686 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   16                 64                  3                 0          1.49928e-05         27        1            968.68          0.34862  │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  5                 1          6.88631e-05         23        1            891.395         0.326385 │
│ trial_8aa9a    TERMINATED           2   rmsprop         relu                                   16                 64                  3                 1          9.98374e-05         28        1            749.19          0.333929 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   16                 64                  5                 1          3.67906e-05         27        1            955.282         0.320826 │
│ trial_8aa9a    TERMINATED           3   rmsprop         tanh                                   16                 64                  3                 0          4.19304e-05         27        1            945.623         0.298987 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   32                 32                  3                 1          1.07123e-05         28        1            853.616         0.281914 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 16                  5                 0          4.89575e-05         18        1            702.225         0.281517 │
│ trial_8aa9a    TERMINATED           2   adam            relu                                   32                 16                  3                 0          0.000139458         20        1            471.914         0.324797 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   32                 64                  3                 1          4.79829e-05         27        1            723.629         0.31348  │
│ trial_8aa9a    TERMINATED           3   rmsprop         tanh                                   16                 32                  3                 1          7.05353e-05         25        1            932.309         0.296605 │
│ trial_8aa9a    TERMINATED           2   adam            tanh                                   16                 16                  5                 0          0.000121681         24        1            886.683         0.30812  │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 64                  3                 1          0.000190495         29        1            679.655         0.323407 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 16                  3                 0          4.87332e-05         16        1            478.719         0.288068 │
│ trial_8aa9a    TERMINATED           3   adam            relu                                   16                 32                  3                 1          7.28445e-05         27        1            938.011         0.353981 │
│ trial_8aa9a    TERMINATED           3   rmsprop         tanh                                   16                 16                  5                 1          1.44289e-05         29        1            977.154         0.272186 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   16                 32                  3                 1          4.18709e-05         16        1            876.218         0.328767 │
│ trial_8aa9a    TERMINATED           2   rmsprop         tanh                                   16                 32                  3                 1          1.96633e-05         26        1            940.536         0.304943 │
│ trial_8aa9a    TERMINATED           3   rmsprop         relu                                   16                 32                  3                 1          5.18588e-06         17        1            906.48          0.234862 │
│ trial_8aa9a    TERMINATED           3   adam            tanh                                   32                 32                  3                 1          5.57279e-05         28        1            861.291         0.296407 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Mejores hiperparámetros: {'N_capas': 3, 'optimizador': 'adam', 'funcion_activacion': 'relu', 'tamanho_minilote': 16, 'numero_filtros': 32, 'tamanho_filtro': 3, 'num_resblocks': 1, 'tasa_aprendizaje': 7.284454600054368e-05, 'epochs': 27}
[36m(train_cnn_ray_tune pid=2697856)[0m 
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step
Epoch 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762516604.768185 2749251 service.cc:152] XLA service 0x7e616c0317e0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762516604.768218 2749251 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 12:56:44.834938: 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 00:00:1762516605.279008 2749251 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762516607.883685 2749251 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:47:22[0m 6s/step - accuracy: 0.0625 - loss: 3.3309
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1077 - loss: 3.1941    
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0972 - loss: 3.2464
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0910 - loss: 3.2569
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0884 - loss: 3.2584
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0882 - loss: 3.2549
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0888 - loss: 3.2479
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0898 - loss: 3.2419
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0915 - loss: 3.2351
[1m 255/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0936 - loss: 3.2276
[1m 283/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0956 - loss: 3.2192
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0976 - loss: 3.2103
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0996 - loss: 3.2020
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1014 - loss: 3.1937
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1030 - loss: 3.1860
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1045 - loss: 3.1786
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1059 - loss: 3.1715
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1073 - loss: 3.1646
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1085 - loss: 3.1585
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1097 - loss: 3.1518
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1108 - loss: 3.1455
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1117 - loss: 3.1395
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1126 - loss: 3.1343
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1136 - loss: 3.1285
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1144 - loss: 3.1233
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1152 - loss: 3.1181
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1159 - loss: 3.1133
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1167 - loss: 3.1079
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1174 - loss: 3.1035
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1182 - loss: 3.0988
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1189 - loss: 3.0942
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1196 - loss: 3.0895
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1202 - loss: 3.0852
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1210 - loss: 3.0804
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1216 - loss: 3.0763
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1222 - loss: 3.0721
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1228 - loss: 3.0682
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1235 - loss: 3.0641
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1239 - loss: 3.0608
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1245 - loss: 3.0570
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1251 - loss: 3.0532
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1257 - loss: 3.0494
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1261 - loss: 3.0467
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1261 - loss: 3.0466 - val_accuracy: 0.2402 - val_loss: 2.3739
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.3125 - loss: 2.3947
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1931 - loss: 2.5460  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6178
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1807 - loss: 2.6341
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6434
[1m 144/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6494
[1m 174/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1806 - loss: 2.6504
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1816 - loss: 2.6499
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1821 - loss: 2.6500
[1m 254/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6502
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6499
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1831 - loss: 2.6497
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1834 - loss: 2.6499
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1837 - loss: 2.6501
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.6503
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1841 - loss: 2.6503
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1843 - loss: 2.6500
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.6498
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.6494
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.6489
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1849 - loss: 2.6479
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1851 - loss: 2.6469
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6460
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.6452
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1856 - loss: 2.6444
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6437
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.6429
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.6422
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1861 - loss: 2.6414
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.6407
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6399
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1865 - loss: 2.6392
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1866 - loss: 2.6386
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1868 - loss: 2.6377
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1869 - loss: 2.6369
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1871 - loss: 2.6360
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1873 - loss: 2.6352
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.6343
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1876 - loss: 2.6334
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1878 - loss: 2.6325
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.6318
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1881 - loss: 2.6310
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1882 - loss: 2.6303 - val_accuracy: 0.2672 - val_loss: 2.2509
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4297
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2235 - loss: 2.5547  
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.5706
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2130 - loss: 2.5619
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2133 - loss: 2.5498
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2129 - loss: 2.5417
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2123 - loss: 2.5360
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2125 - loss: 2.5307
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2128 - loss: 2.5266
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2129 - loss: 2.5242
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2127 - loss: 2.5219
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2125 - loss: 2.5199
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.5179
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2123 - loss: 2.5159
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2123 - loss: 2.5140
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2123 - loss: 2.5120
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.5100
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.5082
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.5064
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2125 - loss: 2.5052
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2126 - loss: 2.5040
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2127 - loss: 2.5028
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2127 - loss: 2.5018
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2128 - loss: 2.5008
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2129 - loss: 2.4999
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4991
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.4982
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.4973
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.4965
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.4959
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.4953
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.4946
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.4940
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.4934
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2131 - loss: 2.4929
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4925
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4921
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4917
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4914
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4911
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2129 - loss: 2.4907
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4903
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4901 - val_accuracy: 0.2922 - val_loss: 2.2160
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1250 - loss: 2.5940
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2117 - loss: 2.5025  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4988
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4916
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2193 - loss: 2.4826
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2199 - loss: 2.4754
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2202 - loss: 2.4685
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2200 - loss: 2.4641
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2198 - loss: 2.4608
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2197 - loss: 2.4581
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2193 - loss: 2.4562
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4544
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4525
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4505
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4485
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4468
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2181 - loss: 2.4456
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4442
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2179 - loss: 2.4430
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4417
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4405
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4392
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2179 - loss: 2.4380
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4367
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2181 - loss: 2.4355
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4343
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4332
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4323
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4313
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4303
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4294
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4285
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4277
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2191 - loss: 2.4269
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4262
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2193 - loss: 2.4254
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4246
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2195 - loss: 2.4239
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2196 - loss: 2.4233
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2198 - loss: 2.4226
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2198 - loss: 2.4220
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2199 - loss: 2.4214
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2200 - loss: 2.4209 - val_accuracy: 0.3093 - val_loss: 2.1579
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2485
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2245 - loss: 2.3896  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3622
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3575
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2327 - loss: 2.3506
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3454
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.3426
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2376 - loss: 2.3427
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2378 - loss: 2.3429
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3426
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2378 - loss: 2.3426
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2380 - loss: 2.3419
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2381 - loss: 2.3412
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2383 - loss: 2.3405
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2384 - loss: 2.3400
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2384 - loss: 2.3396
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2386 - loss: 2.3392
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2387 - loss: 2.3390
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2389 - loss: 2.3385
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2391 - loss: 2.3379
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2394 - loss: 2.3373
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2396 - loss: 2.3368
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2397 - loss: 2.3364
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2399 - loss: 2.3361
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2400 - loss: 2.3356
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2401 - loss: 2.3352
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2403 - loss: 2.3349
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2404 - loss: 2.3345
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2405 - loss: 2.3343
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2406 - loss: 2.3340
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2407 - loss: 2.3338
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2408 - loss: 2.3335
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2409 - loss: 2.3332
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.3330
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2412 - loss: 2.3327
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2413 - loss: 2.3325
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2413 - loss: 2.3323
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2415 - loss: 2.3320
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2415 - loss: 2.3318
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.3317
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.3315
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.3314
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.3313
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2416 - loss: 2.3313 - val_accuracy: 0.3091 - val_loss: 2.1492
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2522
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2419 - loss: 2.2962  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2375 - loss: 2.3336
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3373
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2351 - loss: 2.3385
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2358 - loss: 2.3367
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2373 - loss: 2.3329
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2393 - loss: 2.3287
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2406 - loss: 2.3255
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2417 - loss: 2.3237
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.3217
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2439 - loss: 2.3200
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2450 - loss: 2.3180
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2459 - loss: 2.3163
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2467 - loss: 2.3146
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2476 - loss: 2.3129
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2484 - loss: 2.3114
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2491 - loss: 2.3099
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.3088
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2503 - loss: 2.3075
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2509 - loss: 2.3064
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2514 - loss: 2.3054
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2518 - loss: 2.3043
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2523 - loss: 2.3034
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2527 - loss: 2.3024
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2531 - loss: 2.3016
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2533 - loss: 2.3009
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2536 - loss: 2.3003
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2998
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2993
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2988
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2983
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2978
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2972
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2967
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2962
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2956
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2951
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2946
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2942
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2938
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2934
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2931
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2930 - val_accuracy: 0.3300 - val_loss: 2.1429
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.1557
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2725 - loss: 2.2096  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2645 - loss: 2.2288
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2402
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2446
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2479
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2495
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2487
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2477
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2467
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2457
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2566 - loss: 2.2456
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2572 - loss: 2.2454
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2576 - loss: 2.2455
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2580 - loss: 2.2454
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2453
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2451
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2448
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2447
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2447
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2448
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2450
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2453
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2456
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2458
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2459
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2460
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2461
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2461
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2461
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2461
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2462
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2462
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2462
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2462
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2461
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2461
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2460
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2610 - loss: 2.2459
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2610 - loss: 2.2459
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2458
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2458
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2612 - loss: 2.2457
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2612 - loss: 2.2457 - val_accuracy: 0.3548 - val_loss: 2.1333
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9282
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2669 - loss: 2.1407  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1549
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1689
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2714 - loss: 2.1767
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1812
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.1845
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2731 - loss: 2.1880
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2724 - loss: 2.1910
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2718 - loss: 2.1943
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.1970
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.1989
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.2004
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.2015
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.2026
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.2039
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2713 - loss: 2.2054
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2712 - loss: 2.2064
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2711 - loss: 2.2072
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.2081
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.2087
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.2093
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2708 - loss: 2.2102
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2109
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.2117
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2704 - loss: 2.2124
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.2130
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.2136
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.2141
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.2145
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.2148
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.2151
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.2154
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.2156
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2158
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2159
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2160
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2160
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2160
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2160
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2693 - loss: 2.2161
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2693 - loss: 2.2160
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2693 - loss: 2.2161
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2693 - loss: 2.2161 - val_accuracy: 0.3446 - val_loss: 2.1093
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2074
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1737  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1706
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1828
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1918
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1975
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2687 - loss: 2.2012
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.2052
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2662 - loss: 2.2076
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2657 - loss: 2.2089
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2652 - loss: 2.2098
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2650 - loss: 2.2100
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2649 - loss: 2.2098
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2649 - loss: 2.2095
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2648 - loss: 2.2091
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2647 - loss: 2.2090
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2645 - loss: 2.2088
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2645 - loss: 2.2085
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2647 - loss: 2.2082
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2648 - loss: 2.2080
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2650 - loss: 2.2077
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2652 - loss: 2.2073
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 2.2069
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2656 - loss: 2.2066
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2657 - loss: 2.2063
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2658 - loss: 2.2061
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2659 - loss: 2.2059
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2056
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2662 - loss: 2.2052
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2663 - loss: 2.2049
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2665 - loss: 2.2045
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2667 - loss: 2.2042
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2668 - loss: 2.2039
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2670 - loss: 2.2036
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2671 - loss: 2.2033
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2672 - loss: 2.2029
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2674 - loss: 2.2027
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2675 - loss: 2.2023
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2677 - loss: 2.2020
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2678 - loss: 2.2017
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2679 - loss: 2.2014
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2680 - loss: 2.2011
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2681 - loss: 2.2009
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2682 - loss: 2.2006 - val_accuracy: 0.3496 - val_loss: 2.0886
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1595
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2623 - loss: 2.2485  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2214
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2675 - loss: 2.2128
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2678 - loss: 2.2090
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.2032
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2712 - loss: 2.2020
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2733 - loss: 2.2008
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2755 - loss: 2.1999
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1979
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1963
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1947
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1931
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1915
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1901
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1890
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1882
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1878
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1875
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1873
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1874
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1874
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1872
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1869
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1866
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1861
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1857
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1854
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1850
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1848
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1846
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1844
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1842
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1839
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1837
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1834
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1832
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1829
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1827
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1824
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1822
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1820
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1818
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1817 - val_accuracy: 0.3550 - val_loss: 2.0779
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.1932
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.1790  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1578
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1492
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1452
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1449
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1445
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1450
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1473
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1491
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1503
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1508
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1512
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1513
[1m 393/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1514
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1513
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1512
[1m 476/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1509
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1507
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1504
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1500
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1496
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1493
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1491
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1488
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1487
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1485
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1483
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1482
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1482
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1482
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1482
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1481
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2869 - loss: 2.1480
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2869 - loss: 2.1479
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1479
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1478
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1477
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1476
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2872 - loss: 2.1475
[1m1103/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2872 - loss: 2.1475
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1475
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1475 - val_accuracy: 0.3578 - val_loss: 2.0598
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.8343
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0899  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3074 - loss: 2.1153
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3113 - loss: 2.1076
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 2.1036
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 2.1005
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0972
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0959
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0964
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0964
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0970
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 2.0975
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0982
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0989
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0995
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 2.1004
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.1015
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.1027
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 2.1038
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 2.1047
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 2.1055
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3023 - loss: 2.1060
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3019 - loss: 2.1066
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1071
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3012 - loss: 2.1076
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1080
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1085
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1089
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3000 - loss: 2.1092
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1095
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1097
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1099
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1101
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1103
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1105
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1107
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 2.1109
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1111
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1112
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1114
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1116
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1117
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2978 - loss: 2.1118
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2978 - loss: 2.1118 - val_accuracy: 0.3544 - val_loss: 2.0661
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9461
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2902 - loss: 2.0489  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2832 - loss: 2.0747
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2872 - loss: 2.0826
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.0932
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1013
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2900 - loss: 2.1049
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2907 - loss: 2.1072
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 2.1075
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1068
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1060
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1055
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1055
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1058
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2936 - loss: 2.1061
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 2.1066
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1067
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1067
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1067
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1068
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1067
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2957 - loss: 2.1066
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.1064
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2964 - loss: 2.1063
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1061
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2971 - loss: 2.1059
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1056
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 2.1053
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1050
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1048
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1047
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 2.1045
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2988 - loss: 2.1044
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1043
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1041
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2993 - loss: 2.1039
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1038
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1036
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1035
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1033
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1030
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1028
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1026
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1025 - val_accuracy: 0.3506 - val_loss: 2.0587
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.1875 - loss: 2.4021
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2648 - loss: 2.2211  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1877
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1693
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1561
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1481
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1432
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1381
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1330
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 2.1283
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 2.1244
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3054 - loss: 2.1210
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3066 - loss: 2.1173
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3073 - loss: 2.1146
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3078 - loss: 2.1124
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 2.1100
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3088 - loss: 2.1081
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.1064
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3096 - loss: 2.1048
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.1033
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.1020
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.1008
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0999
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0992
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0985
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0980
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0976
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0971
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0967
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0964
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0960
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0956
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0953
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0950
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0948
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0946
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0945
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0944
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0942
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0941
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0940
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0939
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0937
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0937 - val_accuracy: 0.3456 - val_loss: 2.0681
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0804
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3373 - loss: 2.0622  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3284 - loss: 2.0525
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 2.0424
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0343
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0321
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0312
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0325
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0348
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0374
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0397
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0419
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0433
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0445
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0453
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0463
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0474
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0485
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0498
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0509
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0518
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0525
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3215 - loss: 2.0532
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0537
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0541
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0544
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0548
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0551
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0554
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0556
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0557
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0559
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0560
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0562
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0563
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0564
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0565
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0567
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0569
[1m1103/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0571
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0573
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0575 - val_accuracy: 0.3589 - val_loss: 2.0708
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.3750 - loss: 2.0429
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3407 - loss: 2.0900  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3373 - loss: 2.0793
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3328 - loss: 2.0665
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3322 - loss: 2.0581
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 2.0554
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 2.0547
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 2.0535
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0533
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0533
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0533
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0533
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3300 - loss: 2.0534
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3298 - loss: 2.0534
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3298 - loss: 2.0530
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 2.0528
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3295 - loss: 2.0528
[1m 470/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3295 - loss: 2.0527
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 2.0525
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 2.0522
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 2.0518
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 2.0515
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 2.0514
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3297 - loss: 2.0512
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3297 - loss: 2.0511
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3297 - loss: 2.0511
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3296 - loss: 2.0510
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3295 - loss: 2.0511
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3294 - loss: 2.0512
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3292 - loss: 2.0513
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3291 - loss: 2.0513
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3290 - loss: 2.0513
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3289 - loss: 2.0512
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3288 - loss: 2.0511
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3287 - loss: 2.0510
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3287 - loss: 2.0509
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3286 - loss: 2.0508
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3285 - loss: 2.0508
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 2.0507
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 2.0507
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3283 - loss: 2.0507
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3282 - loss: 2.0506
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3281 - loss: 2.0506
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3281 - loss: 2.0506 - val_accuracy: 0.3589 - val_loss: 2.0827
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9360
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3118 - loss: 1.9975  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3261 - loss: 1.9849
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3310 - loss: 1.9774
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3362 - loss: 1.9709
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3381 - loss: 1.9697
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.9722
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3388 - loss: 1.9752
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.9785
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3381 - loss: 1.9814
[1m 284/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3378 - loss: 1.9841
[1m 312/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3377 - loss: 1.9861
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3377 - loss: 1.9876
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3377 - loss: 1.9886
[1m 393/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3377 - loss: 1.9898
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3377 - loss: 1.9909
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3376 - loss: 1.9920
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3375 - loss: 1.9930
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3374 - loss: 1.9940
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3373 - loss: 1.9949
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3372 - loss: 1.9957
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3372 - loss: 1.9964
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3372 - loss: 1.9971
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.9978
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3369 - loss: 1.9985
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3367 - loss: 1.9994
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3365 - loss: 2.0001
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 2.0007
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 2.0013
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3362 - loss: 2.0019
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 2.0024
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 2.0030
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3358 - loss: 2.0036
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3357 - loss: 2.0040
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3357 - loss: 2.0045
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3356 - loss: 2.0049
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3355 - loss: 2.0054
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3354 - loss: 2.0059
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3352 - loss: 2.0064
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3351 - loss: 2.0070
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3350 - loss: 2.0076
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3348 - loss: 2.0081
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3347 - loss: 2.0087
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3347 - loss: 2.0088 - val_accuracy: 0.3538 - val_loss: 2.0598
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 1.9110
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3371 - loss: 2.0078  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0288
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0413
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0467
[1m 145/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0483
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3188 - loss: 2.0477
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 2.0472
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0461
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0449
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0439
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0432
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0425
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0413
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0398
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0384
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0372
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0361
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0353
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3238 - loss: 2.0345
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0336
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0328
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 2.0322
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0316
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0312
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0308
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0303
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0299
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 2.0294
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0289
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0285
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0281
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0278
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0275
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0271
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0269
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0267
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0265
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0263
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0261
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0258
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0255
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0253
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0250 - val_accuracy: 0.3468 - val_loss: 2.0610

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m56s[0m 662ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 946us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/step
Saved model to disk.
2025-11-07 12:57:53.038083: 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`.
2025-11-07 12:57:53.049792: 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 00:00:1762516673.063037 2752224 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762516673.067174 2752224 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762516673.077124 2752224 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516673.077145 2752224 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516673.077148 2752224 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516673.077150 2752224 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 12:57:53.080381: 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 00:00:1762516675.359203 2752224 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762516678.403559 2752332 service.cc:152] XLA service 0x70ed04003790 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762516678.403616 2752332 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 12:57:58.476703: 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 00:00:1762516678.915564 2752332 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762516681.475881 2752332 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:33[0m 5s/step - accuracy: 0.1250 - loss: 3.0593
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.0680 - loss: 3.3343    
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0721 - loss: 3.2901
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0755 - loss: 3.2714
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0775 - loss: 3.2612
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0786 - loss: 3.2518
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0799 - loss: 3.2422
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0819 - loss: 3.2324
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0836 - loss: 3.2237
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0850 - loss: 3.2160
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0864 - loss: 3.2079
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0876 - loss: 3.2005
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0888 - loss: 3.1936
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0900 - loss: 3.1869
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0911 - loss: 3.1803
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0923 - loss: 3.1736
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0934 - loss: 3.1669
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0944 - loss: 3.1610
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0954 - loss: 3.1550
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0964 - loss: 3.1491
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0974 - loss: 3.1435
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0984 - loss: 3.1379
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0992 - loss: 3.1326
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1001 - loss: 3.1273
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1009 - loss: 3.1221
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1016 - loss: 3.1180
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1025 - loss: 3.1132
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1032 - loss: 3.1089
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1040 - loss: 3.1048
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1047 - loss: 3.1004
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1054 - loss: 3.0965
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1062 - loss: 3.0921
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1070 - loss: 3.0877
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1077 - loss: 3.0839
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1084 - loss: 3.0796
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1092 - loss: 3.0752
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1100 - loss: 3.0710
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1107 - loss: 3.0670
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1115 - loss: 3.0631
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1121 - loss: 3.0594
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1128 - loss: 3.0559
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1134 - loss: 3.0525
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1139 - loss: 3.0500
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1139 - loss: 3.0498 - val_accuracy: 0.2253 - val_loss: 2.3798
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 31ms/step - accuracy: 0.2500 - loss: 2.3054
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1509 - loss: 2.7284  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1523 - loss: 2.7142
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1556 - loss: 2.7181
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1578 - loss: 2.7172
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1602 - loss: 2.7137
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1622 - loss: 2.7109
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1640 - loss: 2.7071
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1652 - loss: 2.7048
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1662 - loss: 2.7028
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1672 - loss: 2.7002
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1681 - loss: 2.6964
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1691 - loss: 2.6928
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1698 - loss: 2.6900
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1705 - loss: 2.6876
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1711 - loss: 2.6853
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1717 - loss: 2.6832
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1723 - loss: 2.6812
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1728 - loss: 2.6795
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1732 - loss: 2.6779
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1735 - loss: 2.6762
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1739 - loss: 2.6746
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1742 - loss: 2.6730
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1746 - loss: 2.6712
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1749 - loss: 2.6696
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1753 - loss: 2.6679
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1756 - loss: 2.6661
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1759 - loss: 2.6644
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1762 - loss: 2.6628
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1765 - loss: 2.6611
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1768 - loss: 2.6596
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1771 - loss: 2.6581
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1773 - loss: 2.6566
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1775 - loss: 2.6552
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1777 - loss: 2.6539
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6526
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6514
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1783 - loss: 2.6503
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1785 - loss: 2.6490
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1786 - loss: 2.6480
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1788 - loss: 2.6468
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1790 - loss: 2.6457
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.6445
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1792 - loss: 2.6441 - val_accuracy: 0.2573 - val_loss: 2.2544
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0761
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2548 - loss: 2.3521  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2305 - loss: 2.4296
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.4642
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2142 - loss: 2.4787
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.4878
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2079 - loss: 2.4906
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2068 - loss: 2.4926
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2056 - loss: 2.4948
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2050 - loss: 2.4960
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2044 - loss: 2.4975
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2038 - loss: 2.4986
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2034 - loss: 2.4991
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2030 - loss: 2.4989
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2028 - loss: 2.4990
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2026 - loss: 2.4995
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2026 - loss: 2.4997
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2027 - loss: 2.4994
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2028 - loss: 2.4992
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2029 - loss: 2.4990
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2031 - loss: 2.4987
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2032 - loss: 2.4982
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2033 - loss: 2.4978
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2034 - loss: 2.4974
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2035 - loss: 2.4970
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2036 - loss: 2.4965
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2038 - loss: 2.4959
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2039 - loss: 2.4954
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2040 - loss: 2.4948
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.4942
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2042 - loss: 2.4936
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.4929
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.4922
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2047 - loss: 2.4915
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2048 - loss: 2.4907
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2050 - loss: 2.4900
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2051 - loss: 2.4893
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2053 - loss: 2.4885
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2054 - loss: 2.4879
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2055 - loss: 2.4873
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2056 - loss: 2.4868
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4863
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4862 - val_accuracy: 0.2722 - val_loss: 2.2112
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.4819
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2559 - loss: 2.3816  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2505 - loss: 2.3676
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2445 - loss: 2.3738
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.3822
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.3884
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3943
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2326 - loss: 2.3999
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2309 - loss: 2.4039
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2297 - loss: 2.4064
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2289 - loss: 2.4079
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2281 - loss: 2.4090
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2274 - loss: 2.4099
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2269 - loss: 2.4104
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2265 - loss: 2.4106
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2262 - loss: 2.4106
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2260 - loss: 2.4105
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2256 - loss: 2.4106
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2253 - loss: 2.4107
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2249 - loss: 2.4106
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2247 - loss: 2.4103
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.4098
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4093
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4087
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4082
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4077
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4073
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4068
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4062
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4057
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4053
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4049
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4045
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4041
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4037
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4034
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4031
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4028
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4024
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4021
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4018
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2245 - loss: 2.4016 - val_accuracy: 0.3038 - val_loss: 2.1817
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2500 - loss: 2.1226
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2750  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2506 - loss: 2.3069
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3221
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2396 - loss: 2.3270
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.3311
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2351 - loss: 2.3326
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3344
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3366
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3384
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3399
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2331 - loss: 2.3401
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2331 - loss: 2.3401
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3398
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2331 - loss: 2.3394
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3393
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3394
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2328 - loss: 2.3397
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2326 - loss: 2.3400
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2324 - loss: 2.3403
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3405
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3408
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3412
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3414
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3416
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3418
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3418
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3418
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3417
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3416
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3415
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3414
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3412
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3410
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3409
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3408
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3407
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3406
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3404
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3403
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3402
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3400
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3400 - val_accuracy: 0.3105 - val_loss: 2.1656
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4513
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2011 - loss: 2.3515  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2180 - loss: 2.3258
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2264 - loss: 2.3141
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2294 - loss: 2.3110
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3069
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3033
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2350 - loss: 2.3013
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2362 - loss: 2.2996
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2375 - loss: 2.2985
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2387 - loss: 2.2977
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2397 - loss: 2.2972
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2404 - loss: 2.2970
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2413 - loss: 2.2964
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2420 - loss: 2.2959
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2426 - loss: 2.2956
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2430 - loss: 2.2954
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2437 - loss: 2.2948
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2443 - loss: 2.2940
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2446 - loss: 2.2934
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2449 - loss: 2.2929
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.2925
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2452 - loss: 2.2922
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2454 - loss: 2.2918
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2456 - loss: 2.2915
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2457 - loss: 2.2914
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2458 - loss: 2.2912
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2459 - loss: 2.2911
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.2910
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.2908
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.2906
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2903
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2901
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.2900
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.2897
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.2895
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2466 - loss: 2.2892
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2890
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.2887
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.2885
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2883
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2880
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2878
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2877 - val_accuracy: 0.3153 - val_loss: 2.1527
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2408
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1996  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1994
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2731 - loss: 2.2105
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2702 - loss: 2.2183
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.2252
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.2309
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2364
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2624 - loss: 2.2398
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2427
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2452
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2473
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2490
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2504
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2586 - loss: 2.2517
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2528
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2539
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.2548
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.2554
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2569 - loss: 2.2559
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2567 - loss: 2.2564
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2568
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2571
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2574
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2576
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2576
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2577
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2577
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2575
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2572
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2570
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2568
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2566
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2564
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2563
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2562
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2561
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2559
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2558
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2556
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2554
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2552
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2551 - val_accuracy: 0.3345 - val_loss: 2.1193
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1082
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2656 - loss: 2.1626  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2616 - loss: 2.1772
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2620 - loss: 2.1848
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 2.1866
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2652 - loss: 2.1888
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2669 - loss: 2.1899
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2680 - loss: 2.1910
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2685 - loss: 2.1920
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.1930
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2691 - loss: 2.1939
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.1945
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2701 - loss: 2.1949
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1951
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1954
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1959
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1967
[1m 470/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1975
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1981
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1985
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1989
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1994
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1998
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2002
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2004
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2007
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2009
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2012
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2015
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.2018
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.2020
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.2022
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.2024
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.2026
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.2029
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.2031
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2696 - loss: 2.2034
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.2037
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2039
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2693 - loss: 2.2041
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2692 - loss: 2.2043
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2691 - loss: 2.2045
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2691 - loss: 2.2046
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2691 - loss: 2.2046 - val_accuracy: 0.3246 - val_loss: 2.1203
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.7485
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2648 - loss: 2.1350  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2638 - loss: 2.1496
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2633 - loss: 2.1597
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2641 - loss: 2.1650
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2647 - loss: 2.1689
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2656 - loss: 2.1713
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2661 - loss: 2.1746
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2669 - loss: 2.1760
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.1762
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.1763
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2694 - loss: 2.1764
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2698 - loss: 2.1767
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2701 - loss: 2.1774
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1780
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1784
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1788
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1791
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1794
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1795
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1796
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1797
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1798
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1800
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1802
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.1804
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1806
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1808
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1811
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1814
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1816
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1819
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.1823
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.1826
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1829
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1832
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1834
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1836
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1839
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1841
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1844
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1846
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2707 - loss: 2.1848 - val_accuracy: 0.3180 - val_loss: 2.1154
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.2764
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2131  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1988
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1997
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2801 - loss: 2.2009
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.2010
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1992
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1968
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1933
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1904
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1882
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1871
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1865
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1861
[1m 393/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1857
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1852
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1846
[1m 476/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1841
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1836
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1832
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1826
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1822
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1819
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1816
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1814
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1813
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1812
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1811
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1810
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1809
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1808
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1806
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1804
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1804
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1803
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1802
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1801
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1800
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1799
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1798
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1797
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1796
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1796 - val_accuracy: 0.3383 - val_loss: 2.1104
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8795
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1648  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1733
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1761
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2751 - loss: 2.1773
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1733
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1711
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1700
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1691
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1676
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1657
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1642
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1632
[1m 366/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1628
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1626
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1624
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1623
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1619
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1618
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1617
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1615
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1612
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1610
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1608
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1606
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1603
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1601
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1599
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1595
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1593
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1591
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1590
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1587
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1585
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1584
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1583
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1581
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1579
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1577
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1575
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1573
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1570
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1568 - val_accuracy: 0.3147 - val_loss: 2.1030
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0025
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3356 - loss: 2.0477  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0824
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0888
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0933
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0946
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0959
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0981
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 2.1000
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.1012
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.1018
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.1020
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.1021
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 2.1025
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 2.1036
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 2.1049
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3034 - loss: 2.1061
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3031 - loss: 2.1072
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 2.1081
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3025 - loss: 2.1088
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3022 - loss: 2.1095
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3019 - loss: 2.1103
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1110
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3014 - loss: 2.1116
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1122
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1128
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1134
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1138
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3000 - loss: 2.1143
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1147
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1150
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1153
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1157
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1161
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2988 - loss: 2.1164
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 2.1167
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1169
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1172
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1174
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1176
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2978 - loss: 2.1177
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 2.1178
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2977 - loss: 2.1178 - val_accuracy: 0.3276 - val_loss: 2.0786
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.0878
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0504  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0799
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0882
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0969
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 2.1046
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 2.1067
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 2.1074
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.1079
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3022 - loss: 2.1088
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3019 - loss: 2.1091
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 2.1091
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1091
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1089
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3015 - loss: 2.1091
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 2.1094
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1095
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1094
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1091
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1087
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1085
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1081
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1078
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1075
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1072
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1068
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1066
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1064
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1064
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1063
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1063
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1062
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1061
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1059
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1059
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1058
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1057
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1056
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1054
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1053
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1051
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1049
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1048 - val_accuracy: 0.3252 - val_loss: 2.0991
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3750 - loss: 1.4542
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2881 - loss: 1.9418  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2922 - loss: 1.9866
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2974 - loss: 2.0064
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2996 - loss: 2.0201
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0305
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 2.0395
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 2.0454
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 2.0495
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0529
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0554
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.0584
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0605
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0625
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0642
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0657
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0668
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0677
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3033 - loss: 2.0685
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0694
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0702
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0708
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 2.0716
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0723
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0729
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3040 - loss: 2.0735
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3041 - loss: 2.0740
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3041 - loss: 2.0745
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0749
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0752
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0755
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0759
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0763
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0765
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0767
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0769
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3049 - loss: 2.0770
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0771
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0772
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0773
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0773
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0773
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0774 - val_accuracy: 0.3276 - val_loss: 2.0810
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9390
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3205 - loss: 1.9832  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0329
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0520
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0565
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0580
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3215 - loss: 2.0577
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0563
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0555
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0553
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0552
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0555
[1m 337/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0560
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0561
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3188 - loss: 2.0559
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0563
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0569
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0574
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0577
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0579
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3165 - loss: 2.0580
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3163 - loss: 2.0582
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3162 - loss: 2.0583
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3161 - loss: 2.0584
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3160 - loss: 2.0584
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3159 - loss: 2.0586
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3158 - loss: 2.0587
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3157 - loss: 2.0588
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 2.0589
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0590
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0591
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0592
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0593
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0593
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0594
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0594
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0594
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0595
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3148 - loss: 2.0595
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3148 - loss: 2.0595
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0595
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0596
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0596 - val_accuracy: 0.3256 - val_loss: 2.0977
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.3708
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3569 - loss: 2.1570  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3379 - loss: 2.1475
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3332 - loss: 2.1285
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 2.1159
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3314 - loss: 2.1065
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3310 - loss: 2.1003
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0944
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 2.0901
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 2.0863
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3289 - loss: 2.0832
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 2.0808
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0790
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0775
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0764
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0760
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0756
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0752
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0749
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0744
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0739
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0732
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0728
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0726
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0723
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0719
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0715
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0711
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0707
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0702
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0697
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0692
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0686
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0682
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0678
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0673
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0668
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0663
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0659
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0654
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0650
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0646
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0646 - val_accuracy: 0.3363 - val_loss: 2.1032
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.8543
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3094 - loss: 1.9970  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0133
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3156 - loss: 2.0150
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0127
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0100
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0108
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0141
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0173
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0196
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0208
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0219
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0230
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0237
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0245
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0250
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0254
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0258
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0261
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3272 - loss: 2.0264
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3272 - loss: 2.0267
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0268
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0268
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0269
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0271
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0274
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0278
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0281
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0284
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0287
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0291
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0294
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0296
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0298
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0300
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0300
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0301
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0302
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0303
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0303
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0303
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0304
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0303 - val_accuracy: 0.3445 - val_loss: 2.0886

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 652ms/step
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 988us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:06[0m 844ms/step
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m102/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m158/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 963us/step
[1m207/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 979us/step
[1m262/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 967us/step
[1m317/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 958us/step
[1m371/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 954us/step
[1m424/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 954us/step
[1m480/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 948us/step
[1m537/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 942us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 933us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 51/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m100/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step
[1m157/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 969us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 34.68 [%]
Global F1 score (validation) = 34.06 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.03096079 0.0143607  0.02476234 ... 0.02604195 0.06098749 0.01087986]
 [0.00448006 0.00278193 0.00288662 ... 0.09030356 0.01493886 0.00796494]
 [0.00110113 0.00070355 0.00046993 ... 0.00740426 0.0007896  0.00242097]
 ...
 [0.13186492 0.02969285 0.20779227 ... 0.00121603 0.23033181 0.16116075]
 [0.2460364  0.03964425 0.12394165 ... 0.00905404 0.1487129  0.13027047]
 [0.12933592 0.05048251 0.2210267  ... 0.0021912  0.18248978 0.10562206]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 39.37 [%]
Global accuracy score (test) = 27.22 [%]
Global F1 score (train) = 39.43 [%]
Global F1 score (test) = 27.12 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.24      0.41      0.30       184
 CAMINAR CON MÓVIL O LIBRO       0.33      0.15      0.20       184
       CAMINAR USUAL SPEED       0.18      0.06      0.09       184
            CAMINAR ZIGZAG       0.19      0.21      0.20       184
          DE PIE BARRIENDO       0.23      0.18      0.20       184
   DE PIE DOBLANDO TOALLAS       0.30      0.31      0.31       184
    DE PIE MOVIENDO LIBROS       0.22      0.33      0.27       184
          DE PIE USANDO PC       0.16      0.21      0.18       184
        FASE REPOSO CON K5       0.56      0.54      0.55       184
INCREMENTAL CICLOERGOMETRO       0.52      0.43      0.47       184
           SENTADO LEYENDO       0.31      0.29      0.30       184
         SENTADO USANDO PC       0.21      0.17      0.19       184
      SENTADO VIENDO LA TV       0.10      0.11      0.11       184
   SUBIR Y BAJAR ESCALERAS       0.23      0.27      0.25       184
                    TROTAR       0.49      0.43      0.46       161

                  accuracy                           0.27      2737
                 macro avg       0.28      0.27      0.27      2737
              weighted avg       0.28      0.27      0.27      2737


Accuracy capturado en la ejecución 1: 27.22 [%]
F1-score capturado en la ejecución 1: 27.12 [%]

=== EJECUCIÓN 2 ===

--- TRAIN (ejecución 2) ---

--- TEST (ejecución 2) ---
2025-11-07 12:59:01.150923: 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`.
2025-11-07 12:59:01.162169: 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 00:00:1762516741.175187 2755149 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762516741.179383 2755149 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762516741.189125 2755149 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516741.189143 2755149 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516741.189146 2755149 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516741.189148 2755149 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 12:59:01.192268: 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 00:00:1762516743.464321 2755149 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13762 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762516746.570362 2755280 service.cc:152] XLA service 0x705820019eb0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762516746.570393 2755280 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 12:59:06.636853: 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 00:00:1762516747.082443 2755280 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762516749.617396 2755280 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45:07[0m 5s/step - accuracy: 0.0625 - loss: 3.5756
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0805 - loss: 3.3113    
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0770 - loss: 3.3322
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0765 - loss: 3.3224
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0786 - loss: 3.3050
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0809 - loss: 3.2883
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0828 - loss: 3.2741
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0847 - loss: 3.2588
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0864 - loss: 3.2459
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0878 - loss: 3.2352
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0892 - loss: 3.2266
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0909 - loss: 3.2162
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0925 - loss: 3.2068
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0941 - loss: 3.1976
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0956 - loss: 3.1888
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0972 - loss: 3.1799
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0985 - loss: 3.1725
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1000 - loss: 3.1645
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1014 - loss: 3.1571
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1027 - loss: 3.1498
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1040 - loss: 3.1426
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1053 - loss: 3.1353
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1065 - loss: 3.1287
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1077 - loss: 3.1219
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1088 - loss: 3.1152
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1099 - loss: 3.1086
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1109 - loss: 3.1027
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1118 - loss: 3.0978
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1127 - loss: 3.0918
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1137 - loss: 3.0863
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1145 - loss: 3.0810
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1154 - loss: 3.0762
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1162 - loss: 3.0712
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1169 - loss: 3.0666
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1176 - loss: 3.0619
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1184 - loss: 3.0566
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1191 - loss: 3.0520
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1197 - loss: 3.0480
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1203 - loss: 3.0434
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1210 - loss: 3.0389
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1217 - loss: 3.0345
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1222 - loss: 3.0307
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1228 - loss: 3.0269
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1232 - loss: 3.0243
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1232 - loss: 3.0241 - val_accuracy: 0.2793 - val_loss: 2.3006
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1250 - loss: 2.9809
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2015 - loss: 2.6645  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1897 - loss: 2.6715
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1876 - loss: 2.6640
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1868 - loss: 2.6562
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1872 - loss: 2.6515
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1875 - loss: 2.6485
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1872 - loss: 2.6474
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1867 - loss: 2.6477
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1867 - loss: 2.6469
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1868 - loss: 2.6456
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1867 - loss: 2.6445
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6438
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1861 - loss: 2.6430
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1859 - loss: 2.6419
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6408
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6396
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.6384
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.6372
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.6359
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.6347
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.6336
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6324
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6312
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.6302
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.6292
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.6282
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.6273
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.6263
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1861 - loss: 2.6253
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1861 - loss: 2.6244
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1861 - loss: 2.6235
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1861 - loss: 2.6226
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.6218
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.6209
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.6202
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.6194
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.6186
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.6178
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.6170
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.6162
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6154
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6146
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6145 - val_accuracy: 0.3012 - val_loss: 2.2246
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1250 - loss: 2.6524
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1835 - loss: 2.5003  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1939 - loss: 2.4911
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1986 - loss: 2.4845
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2017 - loss: 2.4780
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2018 - loss: 2.4776
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2014 - loss: 2.4800
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2009 - loss: 2.4829
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.4843
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.4859
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2011 - loss: 2.4872
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2012 - loss: 2.4880
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2013 - loss: 2.4885
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2014 - loss: 2.4887
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2015 - loss: 2.4886
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2017 - loss: 2.4882
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2018 - loss: 2.4881
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2019 - loss: 2.4879
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.4876
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2023 - loss: 2.4873
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2025 - loss: 2.4868
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2027 - loss: 2.4862
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2031 - loss: 2.4855
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2033 - loss: 2.4849
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2037 - loss: 2.4841
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2039 - loss: 2.4834
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2042 - loss: 2.4828
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.4822
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2047 - loss: 2.4815
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2049 - loss: 2.4809
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2051 - loss: 2.4802
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2053 - loss: 2.4797
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2054 - loss: 2.4792
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2055 - loss: 2.4788
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2056 - loss: 2.4783
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2058 - loss: 2.4778
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2059 - loss: 2.4772
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2060 - loss: 2.4766
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2061 - loss: 2.4761
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2062 - loss: 2.4756
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2063 - loss: 2.4752
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2063 - loss: 2.4748
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.4745
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2064 - loss: 2.4744 - val_accuracy: 0.3045 - val_loss: 2.1990
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.7467
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2174 - loss: 2.3870  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2166 - loss: 2.3832
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2134 - loss: 2.3943
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2144 - loss: 2.3988
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2164 - loss: 2.3991
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.3977
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2205 - loss: 2.3961
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2220 - loss: 2.3945
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2225 - loss: 2.3936
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2227 - loss: 2.3931
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2227 - loss: 2.3925
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2227 - loss: 2.3921
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2227 - loss: 2.3919
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2226 - loss: 2.3918
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2225 - loss: 2.3918
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2224 - loss: 2.3918
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3918
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3918
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2220 - loss: 2.3921
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2219 - loss: 2.3923
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2219 - loss: 2.3923
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2219 - loss: 2.3925
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2219 - loss: 2.3927
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2220 - loss: 2.3928
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2220 - loss: 2.3929
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2221 - loss: 2.3931
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3932
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3933
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2224 - loss: 2.3935
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2224 - loss: 2.3936
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2225 - loss: 2.3938
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2225 - loss: 2.3940
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2226 - loss: 2.3940
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2227 - loss: 2.3940
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2227 - loss: 2.3940
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.3940
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.3939
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.3939
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.3938
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2230 - loss: 2.3937
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2230 - loss: 2.3936
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2230 - loss: 2.3935 - val_accuracy: 0.3173 - val_loss: 2.1712
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3208
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2667 - loss: 2.2987  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2510 - loss: 2.3229
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2435 - loss: 2.3334
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2413 - loss: 2.3338
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2391 - loss: 2.3346
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2374 - loss: 2.3349
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.3350
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3347
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3343
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3337
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3329
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3322
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3319
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3314
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3312
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2331 - loss: 2.3311
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2328 - loss: 2.3314
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2327 - loss: 2.3315
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3316
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2324 - loss: 2.3316
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3316
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3315
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3314
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3315
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3316
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3316
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3316
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3315
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3314
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3312
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2324 - loss: 2.3311
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2324 - loss: 2.3310
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2324 - loss: 2.3309
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3308
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2326 - loss: 2.3306
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2326 - loss: 2.3304
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2327 - loss: 2.3302
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2328 - loss: 2.3300
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3298
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3296
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3293
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2331 - loss: 2.3291
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3290 - val_accuracy: 0.3226 - val_loss: 2.1500
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3702
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2534 - loss: 2.3985  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2472 - loss: 2.3653
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2441 - loss: 2.3548
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2410 - loss: 2.3509
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2390 - loss: 2.3473
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.3438
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2368 - loss: 2.3402
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2366 - loss: 2.3367
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2366 - loss: 2.3340
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2371 - loss: 2.3309
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.3280
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2381 - loss: 2.3256
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2385 - loss: 2.3228
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2390 - loss: 2.3203
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2396 - loss: 2.3177
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2400 - loss: 2.3153
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2404 - loss: 2.3134
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.3119
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2408 - loss: 2.3107
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2410 - loss: 2.3094
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2411 - loss: 2.3084
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2412 - loss: 2.3075
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2413 - loss: 2.3066
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.3057
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.3048
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2418 - loss: 2.3038
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3031
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2421 - loss: 2.3024
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2422 - loss: 2.3018
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2423 - loss: 2.3012
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2424 - loss: 2.3006
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3000
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2426 - loss: 2.2996
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2991
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2986
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2981
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2429 - loss: 2.2976
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.2973
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.2969
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.2965
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2961
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2957
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2954
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2953 - val_accuracy: 0.3200 - val_loss: 2.1374
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.2715
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1952 - loss: 2.3458  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2186 - loss: 2.3169
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2303 - loss: 2.2915
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.2764
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2424 - loss: 2.2668
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2457 - loss: 2.2609
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2565
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2493 - loss: 2.2535
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2500 - loss: 2.2514
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2493
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2515 - loss: 2.2471
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2521 - loss: 2.2456
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2526 - loss: 2.2446
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2529 - loss: 2.2440
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2436
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2433
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2536 - loss: 2.2431
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2431
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2430
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2430
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2428
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2427
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2427
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2427
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2427
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2428
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2428
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2429
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2429
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2430
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2431
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2431
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2431
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2430
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2430
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2430
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2430
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2430
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2430
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2430
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2430
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2431 - val_accuracy: 0.3280 - val_loss: 2.1093
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2320
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2830  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2657 - loss: 2.2550
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2670 - loss: 2.2370
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2681 - loss: 2.2291
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2681 - loss: 2.2264
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.2239
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2691 - loss: 2.2217
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2697 - loss: 2.2193
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2184
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2174
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.2165
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.2154
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.2143
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2132
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2721 - loss: 2.2119
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2722 - loss: 2.2107
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2724 - loss: 2.2098
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2724 - loss: 2.2094
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2723 - loss: 2.2091
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2723 - loss: 2.2089
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2723 - loss: 2.2088
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2721 - loss: 2.2089
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2720 - loss: 2.2089
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.2091
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.2092
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2716 - loss: 2.2094
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2714 - loss: 2.2095
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.2096
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2712 - loss: 2.2098
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.2099
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.2101
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.2103
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2105
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2108
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.2109
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2704 - loss: 2.2111
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2112
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.2113
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.2115
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.2115
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.2115
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.2115
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2697 - loss: 2.2115 - val_accuracy: 0.3236 - val_loss: 2.1407
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0604
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2665 - loss: 2.1756  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2699 - loss: 2.1849
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1921
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1959
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2697 - loss: 2.2013
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2701 - loss: 2.2031
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2702 - loss: 2.2040
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2699 - loss: 2.2058
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2695 - loss: 2.2074
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2691 - loss: 2.2082
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2087
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2687 - loss: 2.2087
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2685 - loss: 2.2084
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.2077
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2687 - loss: 2.2071
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2063
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2689 - loss: 2.2055
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2691 - loss: 2.2047
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.2040
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.2034
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2030
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2695 - loss: 2.2025
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2696 - loss: 2.2020
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.2015
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.2011
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.2007
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.2003
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.1999
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.1995
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.1991
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.1988
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1985
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1982
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1980
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1978
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1976
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1973
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1970
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1967
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1965
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1962
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1959
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1959 - val_accuracy: 0.3218 - val_loss: 2.1171
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9635
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2843 - loss: 2.0986  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2932 - loss: 2.0930
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2915 - loss: 2.1089
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2907 - loss: 2.1191
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1272
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1337
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2874 - loss: 2.1394
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1435
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1456
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1468
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1478
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1487
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2869 - loss: 2.1495
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2872 - loss: 2.1503
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2874 - loss: 2.1511
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2874 - loss: 2.1521
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1529
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1537
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1542
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1546
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1549
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1552
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2869 - loss: 2.1555
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1559
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1562
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1564
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1567
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1569
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1572
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1574
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1576
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1578
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1580
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1580
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1580
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1580
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1580
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1580
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1580
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1579
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1579
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1578
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1578 - val_accuracy: 0.3407 - val_loss: 2.1156
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.9950
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0973  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1194
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2915 - loss: 2.1312
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2886 - loss: 2.1362
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1386
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1423
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1449
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1468
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1486
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1503
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1511
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1515
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1516
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1522
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1526
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1530
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1532
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1533
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1537
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1540
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1541
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1542
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1543
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1541
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1539
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1536
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1533
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1531
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1530
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1528
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1526
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1523
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1521
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1518
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1515
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1513
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1512
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1510
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1508
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1507
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1505
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1502
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1500
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1499 - val_accuracy: 0.3262 - val_loss: 2.1285
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9542
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0313  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0502
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3057 - loss: 2.0639
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0748
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3015 - loss: 2.0806
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.0839
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0863
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.0880
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0888
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0894
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3018 - loss: 2.0899
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0908
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0920
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0935
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0947
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0957
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0964
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0971
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0976
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0980
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0985
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0989
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0994
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0998
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.1001
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.1004
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.1007
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.1010
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.1012
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.1014
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.1015
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3021 - loss: 2.1016
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3021 - loss: 2.1016
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 2.1016
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3019 - loss: 2.1016
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 2.1016
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.1016
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1016
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1016
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 2.1016
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3014 - loss: 2.1017
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1017
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1018 - val_accuracy: 0.3323 - val_loss: 2.1085
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.6169
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2420 - loss: 2.2247  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2032
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2630 - loss: 2.1870
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1690
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1556
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1473
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1410
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1354
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1309
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1269
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2910 - loss: 2.1236
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1208
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1184
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1158
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2955 - loss: 2.1140
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1126
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 2.1112
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1099
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2978 - loss: 2.1090
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1082
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2986 - loss: 2.1073
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1065
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1058
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1050
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1042
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1035
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1029
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1025
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1021
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1016
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1011
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 2.1006
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.1000
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3019 - loss: 2.0995
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0990
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0986
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0982
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0979
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0976
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0973
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0971
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0969
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0968
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0968 - val_accuracy: 0.3468 - val_loss: 2.1064
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.8631
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0386  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0733
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0789
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0835
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0888
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0921
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 2.0926
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 2.0924
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3177 - loss: 2.0926
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0926
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0914
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3165 - loss: 2.0907
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 2.0902
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 2.0902
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0903
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0904
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0904
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0904
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0903
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0903
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0903
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0903
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0904
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0903
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0902
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0900
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0897
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0894
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0892
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0890
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0887
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0886
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0884
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0882
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0881
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0880
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0878
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0877
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0876
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0875
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0873
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0872
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0871 - val_accuracy: 0.3454 - val_loss: 2.1224
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.4375 - loss: 1.5775
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3151 - loss: 1.9530  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3090 - loss: 1.9816
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3138 - loss: 1.9879
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3162 - loss: 1.9941
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3186 - loss: 1.9981
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0027
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0074
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0122
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 2.0171
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0208
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0241
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0272
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3165 - loss: 2.0297
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3159 - loss: 2.0325
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0350
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0371
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0392
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0408
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0421
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0434
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0444
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0452
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0459
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0465
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0470
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0474
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0478
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0482
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0485
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0489
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0492
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0494
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0497
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0500
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0503
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0505
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0508
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0510
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0513
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0516
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0519
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0521
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0522 - val_accuracy: 0.3304 - val_loss: 2.1563
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3831
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3302 - loss: 1.9757  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3294 - loss: 1.9780
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3277 - loss: 1.9831
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3278 - loss: 1.9878
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 1.9889
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 1.9893
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3300 - loss: 1.9915
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 1.9953
[1m 254/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0000
[1m 284/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0037
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0067
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 2.0089
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0106
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0123
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0137
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0146
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0153
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0159
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0165
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0171
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0175
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0178
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0181
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0182
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0184
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0185
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0188
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0191
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0193
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0196
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0200
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0204
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0207
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0211
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0213
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0216
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0219
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0222
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0225
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0228
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0232 - val_accuracy: 0.3300 - val_loss: 2.1566
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0151
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3139 - loss: 1.9760  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0007
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0035
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0077
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3278 - loss: 2.0125
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3272 - loss: 2.0163
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0200
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0221
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0242
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0257
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0269
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0278
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0286
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0292
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0299
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0306
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0311
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0316
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0318
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0318
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0316
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0314
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 2.0313
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0312
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0311
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0310
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0309
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0308
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0307
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0305
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0304
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0303
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0302
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0301
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0300
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0300
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0299
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0299
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0299
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0299
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0299
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0299
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0298
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0297 - val_accuracy: 0.3331 - val_loss: 2.1685
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8457
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3189 - loss: 2.0625  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0775
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0756
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0692
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0627
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0591
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0557
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0535
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0517
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 2.0506
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0494
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0479
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0462
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0446
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0433
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0418
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0404
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0391
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0383
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0375
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0367
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0361
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0356
[1m 644/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0351
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0345
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0341
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0336
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0332
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0328
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0324
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0319
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0314
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0310
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3272 - loss: 2.0305
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0302
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0298
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0295
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0291
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0287
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0284
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0281
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0279
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0277 - val_accuracy: 0.3522 - val_loss: 2.1437

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 636ms/step
[1m49/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:59[0m 830ms/step
[1m 49/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m107/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 950us/step
[1m161/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 945us/step
[1m206/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 985us/step
[1m263/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 964us/step
[1m319/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 952us/step
[1m376/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 942us/step
[1m431/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 939us/step
[1m486/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 936us/step
[1m547/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 925us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 984us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 57/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 901us/step
[1m114/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 895us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 34.45 [%]
Global F1 score (validation) = 33.02 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.00733125 0.00811927 0.01064916 ... 0.03776674 0.03440044 0.00905144]
 [0.00394951 0.00334844 0.00286044 ... 0.09321815 0.01311153 0.00541589]
 [0.00144405 0.00023752 0.00098363 ... 0.00313982 0.00198271 0.00180102]
 ...
 [0.12796894 0.04649103 0.18457249 ... 0.00431485 0.16552632 0.14428085]
 [0.14003447 0.04964171 0.13499855 ... 0.00696937 0.15523353 0.11693389]
 [0.12564938 0.0541793  0.15422745 ... 0.00286224 0.16015102 0.16422799]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 38.7 [%]
Global accuracy score (test) = 29.08 [%]
Global F1 score (train) = 38.58 [%]
Global F1 score (test) = 28.65 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.30      0.45      0.36       184
 CAMINAR CON MÓVIL O LIBRO       0.26      0.28      0.27       184
       CAMINAR USUAL SPEED       0.17      0.10      0.13       184
            CAMINAR ZIGZAG       0.22      0.33      0.26       184
          DE PIE BARRIENDO       0.39      0.23      0.29       184
   DE PIE DOBLANDO TOALLAS       0.44      0.34      0.38       184
    DE PIE MOVIENDO LIBROS       0.34      0.32      0.32       184
          DE PIE USANDO PC       0.10      0.09      0.09       184
        FASE REPOSO CON K5       0.36      0.62      0.45       184
INCREMENTAL CICLOERGOMETRO       0.50      0.45      0.47       184
           SENTADO LEYENDO       0.12      0.10      0.11       184
         SENTADO USANDO PC       0.13      0.12      0.13       184
      SENTADO VIENDO LA TV       0.22      0.21      0.21       184
   SUBIR Y BAJAR ESCALERAS       0.31      0.27      0.28       184
                    TROTAR       0.58      0.50      0.54       161

                  accuracy                           0.29      2737
                 macro avg       0.29      0.29      0.29      2737
              weighted avg       0.29      0.29      0.28      2737


Accuracy capturado en la ejecución 2: 29.08 [%]
F1-score capturado en la ejecución 2: 28.65 [%]

=== EJECUCIÓN 3 ===

--- TRAIN (ejecución 3) ---

--- TEST (ejecución 3) ---
2025-11-07 13:00:12.653080: 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`.
2025-11-07 13:00:12.664421: 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 00:00:1762516812.677535 2758235 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762516812.681659 2758235 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762516812.691606 2758235 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516812.691626 2758235 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516812.691628 2758235 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516812.691629 2758235 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:00:12.694637: 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 00:00:1762516814.992400 2758235 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762516818.049199 2758366 service.cc:152] XLA service 0x72694c007d40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762516818.049238 2758366 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:00:18.115958: 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 00:00:1762516818.556382 2758366 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762516821.094244 2758366 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:15[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.7944
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0395 - loss: 3.5079        
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0500 - loss: 3.4610
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0604 - loss: 3.4241
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0670 - loss: 3.4019
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0716 - loss: 3.3824
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0755 - loss: 3.3652
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0784 - loss: 3.3529
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0810 - loss: 3.3408
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0831 - loss: 3.3294
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0850 - loss: 3.3187
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0869 - loss: 3.3081
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0887 - loss: 3.2982
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0900 - loss: 3.2910
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0915 - loss: 3.2824
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0930 - loss: 3.2733
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0944 - loss: 3.2639
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0957 - loss: 3.2551
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0970 - loss: 3.2461
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0983 - loss: 3.2373
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0995 - loss: 3.2288
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1007 - loss: 3.2207
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1019 - loss: 3.2128
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1030 - loss: 3.2054
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1040 - loss: 3.1987
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1050 - loss: 3.1915
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1060 - loss: 3.1848
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1069 - loss: 3.1787
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1078 - loss: 3.1723
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1086 - loss: 3.1666
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1094 - loss: 3.1609
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1102 - loss: 3.1550
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1109 - loss: 3.1498
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1116 - loss: 3.1449
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1123 - loss: 3.1397
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1130 - loss: 3.1350
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1137 - loss: 3.1299
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1144 - loss: 3.1247
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1151 - loss: 3.1193
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1157 - loss: 3.1145
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1163 - loss: 3.1104
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1170 - loss: 3.1056
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1176 - loss: 3.1010
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1180 - loss: 3.0984
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1180 - loss: 3.0983 - val_accuracy: 0.2500 - val_loss: 2.3294
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.7372
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1921 - loss: 2.6801  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1877 - loss: 2.6928
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1862 - loss: 2.6939
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6914
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1873 - loss: 2.6856
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1870 - loss: 2.6827
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6806
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6788
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6776
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.6763
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1842 - loss: 2.6753
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1840 - loss: 2.6738
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1838 - loss: 2.6728
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.6717
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1835 - loss: 2.6706
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1834 - loss: 2.6696
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1833 - loss: 2.6685
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1832 - loss: 2.6676
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1830 - loss: 2.6668
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.6660
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6651
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6640
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6628
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6618
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6607
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.6597
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1829 - loss: 2.6586
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1830 - loss: 2.6577
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1831 - loss: 2.6566
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1833 - loss: 2.6554
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.6541
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1837 - loss: 2.6528
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1838 - loss: 2.6517
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1840 - loss: 2.6504
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1842 - loss: 2.6492
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1843 - loss: 2.6480
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1845 - loss: 2.6466
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1847 - loss: 2.6454
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.6442
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1850 - loss: 2.6430
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1852 - loss: 2.6420
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6409
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1854 - loss: 2.6403 - val_accuracy: 0.2736 - val_loss: 2.2489
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.2286
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2305 - loss: 2.4703  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4739
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2103 - loss: 2.4763
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4785
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2065 - loss: 2.4816
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2054 - loss: 2.4846
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2043 - loss: 2.4884
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2036 - loss: 2.4920
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2028 - loss: 2.4951
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2022 - loss: 2.4970
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2019 - loss: 2.4983
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2018 - loss: 2.4989
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2017 - loss: 2.4998
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2016 - loss: 2.5006
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2016 - loss: 2.5011
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2016 - loss: 2.5019
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2016 - loss: 2.5024
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2018 - loss: 2.5027
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2019 - loss: 2.5028
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.5028
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2022 - loss: 2.5029
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2024 - loss: 2.5029
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5028
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2029 - loss: 2.5027
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2031 - loss: 2.5024
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2034 - loss: 2.5020
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2036 - loss: 2.5016
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2037 - loss: 2.5012
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2039 - loss: 2.5008
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.5003
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2043 - loss: 2.4999
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.4994
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.4989
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2046 - loss: 2.4984
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2048 - loss: 2.4978
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2048 - loss: 2.4974
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2049 - loss: 2.4968
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2050 - loss: 2.4963
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2051 - loss: 2.4959
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2052 - loss: 2.4954
[1m1103/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2053 - loss: 2.4949
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2054 - loss: 2.4944
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2055 - loss: 2.4939 - val_accuracy: 0.2861 - val_loss: 2.1984
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.4932
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2290 - loss: 2.4200  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2341 - loss: 2.4056
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2372 - loss: 2.3989
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2386 - loss: 2.3979
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2384 - loss: 2.3974
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2384 - loss: 2.3963
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2385 - loss: 2.3958
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.3958
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2378 - loss: 2.3950
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2374 - loss: 2.3941
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2369 - loss: 2.3938
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2367 - loss: 2.3933
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.3931
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2361 - loss: 2.3930
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2357 - loss: 2.3928
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3925
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2354 - loss: 2.3923
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2353 - loss: 2.3922
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2352 - loss: 2.3922
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2351 - loss: 2.3921
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2350 - loss: 2.3919
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3916
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3914
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2347 - loss: 2.3911
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3908
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3906
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3905
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3904
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3904
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.3904
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3905
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3905
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.3905
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3905
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3905
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3905
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3905
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2327 - loss: 2.3905
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3905
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2324 - loss: 2.3904
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3904
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3904 - val_accuracy: 0.3200 - val_loss: 2.1470
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.5921
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1906 - loss: 2.4761  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4088
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2231 - loss: 2.3941
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2243 - loss: 2.3841
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2251 - loss: 2.3759
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2262 - loss: 2.3694
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2275 - loss: 2.3660
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3636
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2301 - loss: 2.3613
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2311 - loss: 2.3593
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3580
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3573
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2328 - loss: 2.3570
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2331 - loss: 2.3567
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3565
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3563
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3563
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3563
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3561
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3559
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3556
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3553
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3550
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3548
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3546
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3544
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3541
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3538
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3536
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3533
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3530
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3529
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3529
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.3529
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.3529
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3529
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3529
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3528
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3527
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3526
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3525
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3524
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3524 - val_accuracy: 0.3276 - val_loss: 2.1341
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1888
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2995 - loss: 2.2049  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 2.2603
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2651 - loss: 2.2815
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2917
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2967
[1m 173/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.3011
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2489 - loss: 2.3038
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2466 - loss: 2.3070
[1m 254/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2447 - loss: 2.3094
[1m 285/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2434 - loss: 2.3111
[1m 312/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.3114
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3108
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2422 - loss: 2.3103
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3098
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2418 - loss: 2.3094
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2416 - loss: 2.3090
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2415 - loss: 2.3086
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2414 - loss: 2.3081
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2413 - loss: 2.3079
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2412 - loss: 2.3077
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2412 - loss: 2.3075
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2412 - loss: 2.3075
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2412 - loss: 2.3074
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2412 - loss: 2.3073
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2413 - loss: 2.3072
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2413 - loss: 2.3070
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.3068
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2415 - loss: 2.3065
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.3061
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2417 - loss: 2.3059
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2418 - loss: 2.3056
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3053
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3051
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2420 - loss: 2.3049
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2421 - loss: 2.3048
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2422 - loss: 2.3046
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2423 - loss: 2.3045
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2423 - loss: 2.3044
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2424 - loss: 2.3043
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2424 - loss: 2.3042
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3041
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3040
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3040 - val_accuracy: 0.3409 - val_loss: 2.1186
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.0625 - loss: 2.3580
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2075  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2376
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2463
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2512
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2518
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2531
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2534
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2521
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2511
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2501
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2495
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2497
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2498
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2612 - loss: 2.2497
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2612 - loss: 2.2497
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2497
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2610 - loss: 2.2498
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2500
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2502
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2505
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2507
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2509
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2509
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2510
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2510
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2511
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2513
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2515
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2516
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2517
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2519
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2520
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2522
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2523
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2525
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2526
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2527
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2529
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2529
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2529
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2529
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2530
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2530 - val_accuracy: 0.3276 - val_loss: 2.1239
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.1875 - loss: 2.2274
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2862  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2516 - loss: 2.2673
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2540
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2571 - loss: 2.2491
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2479
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2473
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2454
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2435
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2415
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2401
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2390
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2378
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2367
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2360
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2353
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2345
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2338
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2331
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2324
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2317
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2311
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2304
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2298
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2293
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2290
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2288
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2286
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2284
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2283
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2282
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2280
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2279
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2278
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2276
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2275
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2273
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2272
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2270
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2268
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2266
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2264
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2262 - val_accuracy: 0.3393 - val_loss: 2.0940
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2648
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2277 - loss: 2.2738  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2385 - loss: 2.2382
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2442 - loss: 2.2304
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2476 - loss: 2.2271
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2248
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2516 - loss: 2.2210
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2178
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2165
[1m 255/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2155
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2144
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2130
[1m 337/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2116
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2102
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2088
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2078
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2069
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2063
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2060
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2055
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2051
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2048
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2046
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2043
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2041
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2040
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2039
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2036
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2610 - loss: 2.2034
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2033
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2613 - loss: 2.2032
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2032
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2031
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2617 - loss: 2.2031
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2031
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2030
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2030
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2621 - loss: 2.2029
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2622 - loss: 2.2029
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2623 - loss: 2.2028
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2624 - loss: 2.2028
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2625 - loss: 2.2027
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2625 - loss: 2.2027 - val_accuracy: 0.3478 - val_loss: 2.0756
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.8618
[1m  31/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1225  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1441
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1594
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2901 - loss: 2.1668
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1704
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1729
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1744
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1752
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1751
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1748
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1745
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1745
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1748
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1753
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1758
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1762
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1766
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1768
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1770
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1773
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1774
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1773
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1770
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1768
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1767
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1766
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1766
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1765
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1764
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1763
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1762
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1760
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1759
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1757
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1756
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2792 - loss: 2.1755
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1754
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1753
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1752
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1751
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1751
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1750
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1750 - val_accuracy: 0.3496 - val_loss: 2.1074
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.7725
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3021 - loss: 2.1317  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1336
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1343
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1378
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1420
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1459
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1494
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1523
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1541
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1554
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1561
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1568
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1571
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1569
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1565
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1564
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1564
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1565
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1565
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1564
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1561
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1558
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1557
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1555
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1552
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1550
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1548
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1546
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1544
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1542
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1540
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1538
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1536
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1534
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1532
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1531
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1529
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1528
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1527
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1526
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1525
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1524
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1524 - val_accuracy: 0.3486 - val_loss: 2.0619
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.9541
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1510  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1615
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1659
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1690
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2748 - loss: 2.1696
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2744 - loss: 2.1687
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2747 - loss: 2.1680
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2751 - loss: 2.1675
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 2.1660
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1636
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1615
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1605
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1593
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1583
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1570
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1558
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1544
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1534
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1522
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1512
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1505
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1498
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1489
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1482
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1476
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1471
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1466
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1462
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1459
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1456
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1453
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1450
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1447
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1444
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1442
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1440
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1438
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1436
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1434
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1432
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1429
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1429 - val_accuracy: 0.3599 - val_loss: 2.0627
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.8933
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3213 - loss: 2.1076  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3104 - loss: 2.1097
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 2.1116
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 2.1089
[1m 145/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.1061
[1m 173/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 2.1050
[1m 202/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3087 - loss: 2.1066
[1m 230/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3079 - loss: 2.1069
[1m 258/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 2.1068
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3066 - loss: 2.1065
[1m 312/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3062 - loss: 2.1062
[1m 337/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 2.1060
[1m 366/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 2.1058
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 2.1057
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 2.1054
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 2.1051
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.1049
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 2.1048
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 2.1048
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 2.1048
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3033 - loss: 2.1050
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3031 - loss: 2.1050
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.1051
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.1052
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.1053
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.1055
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.1057
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 2.1059
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 2.1062
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1064
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 2.1066
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1069
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3012 - loss: 2.1071
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1073
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1075
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1077
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1078
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1079
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1080
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1081
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1082
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1083 - val_accuracy: 0.3409 - val_loss: 2.1178
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.9920
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3515 - loss: 2.0229  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3359 - loss: 2.0392
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0522
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3287 - loss: 2.0584
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0633
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0679
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0725
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0764
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3187 - loss: 2.0797
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0823
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 2.0843
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0858
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0869
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0875
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0881
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0886
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0889
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0892
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0893
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0894
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0895
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0895
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0894
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0891
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0889
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0887
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0885
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0883
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0882
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0881
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0881
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0880
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0880
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3100 - loss: 2.0879
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0879
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0879
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0879
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0879
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0879
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0879
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0879
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0879
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0880 - val_accuracy: 0.3490 - val_loss: 2.0723
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9154
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2977 - loss: 2.0351  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2955 - loss: 2.0598
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2936 - loss: 2.0679
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2954 - loss: 2.0685
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 2.0692
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 2.0711
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 2.0718
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 2.0724
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 2.0728
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 2.0730
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2983 - loss: 2.0728
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2988 - loss: 2.0723
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 2.0718
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 2.0714
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.0712
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.0712
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0714
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0715
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 2.0716
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 2.0717
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0719
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 2.0719
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0719
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 2.0719
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 2.0721
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.0722
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0723
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0724
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0724
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0724
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.0724
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.0724
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 2.0725
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 2.0725
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0725
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 2.0725
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0726
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0726
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0727
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 2.0727
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3019 - loss: 2.0727
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0727
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0727 - val_accuracy: 0.3421 - val_loss: 2.0859
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.4375 - loss: 1.8824
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3739 - loss: 2.0389  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3510 - loss: 2.0393
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3387 - loss: 2.0445
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0522
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3289 - loss: 2.0515
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3278 - loss: 2.0498
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0485
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0483
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0489
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0501
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0510
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0518
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0523
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0528
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0533
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0537
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0541
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0543
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0546
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0550
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0554
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0559
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0562
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0567
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0570
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0573
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0576
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 2.0578
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 2.0579
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3187 - loss: 2.0580
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3186 - loss: 2.0581
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 2.0582
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0582
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3183 - loss: 2.0583
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0583
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0582
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0582
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0581
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 2.0581
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 2.0581
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0581
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0582
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0582 - val_accuracy: 0.3403 - val_loss: 2.0960

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 651ms/step
[1m51/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:10[0m 851ms/step
[1m 49/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m105/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 972us/step
[1m164/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 931us/step
[1m220/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 924us/step
[1m274/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 925us/step
[1m330/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 921us/step
[1m382/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 928us/step
[1m442/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 916us/step
[1m494/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 921us/step
[1m552/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 916us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m57/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 897us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 53/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 973us/step
[1m110/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 932us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 35.22 [%]
Global F1 score (validation) = 34.36 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.01537853 0.01553315 0.01823382 ... 0.04503759 0.05751753 0.00499333]
 [0.00256758 0.00233775 0.00197233 ... 0.12870225 0.00774411 0.00785317]
 [0.00247816 0.00120576 0.00089274 ... 0.00256219 0.00114516 0.00087043]
 ...
 [0.20300193 0.08119979 0.1591507  ... 0.00494025 0.18376717 0.06960166]
 [0.12562807 0.07084877 0.19558874 ... 0.00547585 0.1315866  0.07772345]
 [0.07124586 0.05132472 0.21836445 ... 0.00258999 0.13972229 0.07606315]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 39.22 [%]
Global accuracy score (test) = 28.13 [%]
Global F1 score (train) = 39.21 [%]
Global F1 score (test) = 27.95 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.22      0.29      0.25       184
 CAMINAR CON MÓVIL O LIBRO       0.15      0.17      0.16       184
       CAMINAR USUAL SPEED       0.18      0.18      0.18       184
            CAMINAR ZIGZAG       0.28      0.38      0.32       184
          DE PIE BARRIENDO       0.32      0.17      0.22       184
   DE PIE DOBLANDO TOALLAS       0.30      0.23      0.26       184
    DE PIE MOVIENDO LIBROS       0.20      0.11      0.14       184
          DE PIE USANDO PC       0.17      0.12      0.14       184
        FASE REPOSO CON K5       0.42      0.63      0.51       184
INCREMENTAL CICLOERGOMETRO       0.48      0.43      0.46       184
           SENTADO LEYENDO       0.33      0.32      0.32       184
         SENTADO USANDO PC       0.24      0.23      0.23       184
      SENTADO VIENDO LA TV       0.14      0.22      0.17       184
   SUBIR Y BAJAR ESCALERAS       0.32      0.32      0.32       184
                    TROTAR       0.58      0.45      0.50       161

                  accuracy                           0.28      2737
                 macro avg       0.29      0.28      0.28      2737
              weighted avg       0.29      0.28      0.28      2737


Accuracy capturado en la ejecución 3: 28.13 [%]
F1-score capturado en la ejecución 3: 27.95 [%]

=== EJECUCIÓN 4 ===

--- TRAIN (ejecución 4) ---

--- TEST (ejecución 4) ---
2025-11-07 13:01:18.538519: 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`.
2025-11-07 13:01:18.550351: 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 00:00:1762516878.564520 2761067 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762516878.568909 2761067 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762516878.579332 2761067 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516878.579352 2761067 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516878.579355 2761067 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516878.579356 2761067 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:01:18.582678: 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 00:00:1762516880.832057 2761067 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762516883.920908 2761201 service.cc:152] XLA service 0x7f9368017e70 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762516883.920947 2761201 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:01:23.989046: 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 00:00:1762516884.409064 2761201 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762516886.960737 2761201 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:43[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.4840
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0593 - loss: 3.3137        
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0638 - loss: 3.3394
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0670 - loss: 3.3391
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0703 - loss: 3.3260
[1m 127/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0730 - loss: 3.3132
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0758 - loss: 3.2971
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0781 - loss: 3.2835
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0803 - loss: 3.2703
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0821 - loss: 3.2590
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0840 - loss: 3.2475
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0858 - loss: 3.2375
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0875 - loss: 3.2278
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0892 - loss: 3.2189
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0908 - loss: 3.2103
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0921 - loss: 3.2031
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0934 - loss: 3.1961
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0946 - loss: 3.1897
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0959 - loss: 3.1820
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0971 - loss: 3.1751
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0982 - loss: 3.1692
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0992 - loss: 3.1633
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1002 - loss: 3.1576
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1012 - loss: 3.1513
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1022 - loss: 3.1453
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1032 - loss: 3.1394
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1041 - loss: 3.1338
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1051 - loss: 3.1280
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1060 - loss: 3.1225
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1069 - loss: 3.1170
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1079 - loss: 3.1113
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1089 - loss: 3.1059
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1097 - loss: 3.1012
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1106 - loss: 3.0960
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1114 - loss: 3.0911
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1123 - loss: 3.0863
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1131 - loss: 3.0820
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1138 - loss: 3.0775
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1146 - loss: 3.0731
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1154 - loss: 3.0689
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1161 - loss: 3.0647
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1168 - loss: 3.0608
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1174 - loss: 3.0569
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1177 - loss: 3.0550
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1178 - loss: 3.0549 - val_accuracy: 0.2361 - val_loss: 2.3914
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3125 - loss: 2.4058
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2301 - loss: 2.5723  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2135 - loss: 2.5819
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2078 - loss: 2.5871
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2034 - loss: 2.5919
[1m 127/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2005 - loss: 2.5970
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1977 - loss: 2.6041
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1953 - loss: 2.6115
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1935 - loss: 2.6160
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1923 - loss: 2.6189
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1913 - loss: 2.6214
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1905 - loss: 2.6240
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1897 - loss: 2.6260
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1891 - loss: 2.6275
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1884 - loss: 2.6289
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1878 - loss: 2.6300
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1874 - loss: 2.6311
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1869 - loss: 2.6321
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1865 - loss: 2.6331
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1862 - loss: 2.6335
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1860 - loss: 2.6338
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6338
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6334
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6329
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.6324
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.6318
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1861 - loss: 2.6310
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.6303
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.6293
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1865 - loss: 2.6284
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1866 - loss: 2.6273
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1867 - loss: 2.6264
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1868 - loss: 2.6256
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1869 - loss: 2.6248
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1869 - loss: 2.6238
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1870 - loss: 2.6229
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1871 - loss: 2.6219
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1872 - loss: 2.6210
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1873 - loss: 2.6200
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.6190
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1876 - loss: 2.6181
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1877 - loss: 2.6171
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1878 - loss: 2.6162
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1879 - loss: 2.6154 - val_accuracy: 0.2638 - val_loss: 2.2665
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.6888
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1778 - loss: 2.4797  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1951 - loss: 2.4748
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1967 - loss: 2.4769
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1969 - loss: 2.4776
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1980 - loss: 2.4757
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1986 - loss: 2.4748
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1992 - loss: 2.4744
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1997 - loss: 2.4743
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2000 - loss: 2.4744
[1m 285/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2003 - loss: 2.4746
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2006 - loss: 2.4751
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2006 - loss: 2.4758
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2007 - loss: 2.4763
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2009 - loss: 2.4765
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2012 - loss: 2.4765
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2015 - loss: 2.4761
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2019 - loss: 2.4757
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2023 - loss: 2.4753
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2026 - loss: 2.4750
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2030 - loss: 2.4746
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2033 - loss: 2.4741
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2035 - loss: 2.4736
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2037 - loss: 2.4732
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2039 - loss: 2.4728
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.4724
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2043 - loss: 2.4721
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2044 - loss: 2.4718
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2046 - loss: 2.4715
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2047 - loss: 2.4712
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2049 - loss: 2.4708
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2050 - loss: 2.4704
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2051 - loss: 2.4700
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2053 - loss: 2.4697
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2054 - loss: 2.4694
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2055 - loss: 2.4690
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2056 - loss: 2.4686
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2058 - loss: 2.4682
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2059 - loss: 2.4678
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2061 - loss: 2.4673
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2063 - loss: 2.4668
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.4663
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2066 - loss: 2.4658 - val_accuracy: 0.2857 - val_loss: 2.2535
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.3730
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2571 - loss: 2.4345  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2452 - loss: 2.4240
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2393 - loss: 2.4265
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.4270
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2335 - loss: 2.4261
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2320 - loss: 2.4246
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2310 - loss: 2.4243
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.4253
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2288 - loss: 2.4258
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2284 - loss: 2.4258
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2281 - loss: 2.4254
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2278 - loss: 2.4248
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2275 - loss: 2.4241
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2271 - loss: 2.4226
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2269 - loss: 2.4212
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.4198
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.4182
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2265 - loss: 2.4170
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2264 - loss: 2.4159
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2263 - loss: 2.4148
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2262 - loss: 2.4139
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2261 - loss: 2.4129
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2260 - loss: 2.4119
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2258 - loss: 2.4111
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2257 - loss: 2.4104
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.4098
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.4093
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2252 - loss: 2.4088
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2251 - loss: 2.4082
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2250 - loss: 2.4076
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2249 - loss: 2.4070
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2248 - loss: 2.4064
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2247 - loss: 2.4058
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2247 - loss: 2.4051
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.4044
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.4038
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.4032
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.4025
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.4019
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.4012
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.4005
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.3998
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2246 - loss: 2.3993 - val_accuracy: 0.2946 - val_loss: 2.1764
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0936
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2630  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2502 - loss: 2.2980
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3159
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2439 - loss: 2.3249
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3270
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3274
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3276
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3275
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.3278
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3279
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3276
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3275
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2423 - loss: 2.3276
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2422 - loss: 2.3276
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2420 - loss: 2.3276
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2417 - loss: 2.3279
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2415 - loss: 2.3282
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2413 - loss: 2.3286
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2411 - loss: 2.3288
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2409 - loss: 2.3290
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.3290
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2406 - loss: 2.3289
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2405 - loss: 2.3289
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2404 - loss: 2.3288
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2403 - loss: 2.3289
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2402 - loss: 2.3290
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2401 - loss: 2.3289
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2400 - loss: 2.3290
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2399 - loss: 2.3291
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2397 - loss: 2.3293
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2395 - loss: 2.3295
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2394 - loss: 2.3297
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2392 - loss: 2.3299
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2390 - loss: 2.3300
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2389 - loss: 2.3302
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2387 - loss: 2.3303
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2386 - loss: 2.3304
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2384 - loss: 2.3305
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2383 - loss: 2.3306
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2382 - loss: 2.3306
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2381 - loss: 2.3306
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3305
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3305 - val_accuracy: 0.3028 - val_loss: 2.1719
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.2252
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2994 - loss: 2.3145  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2798 - loss: 2.3116
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2750 - loss: 2.3092
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2712 - loss: 2.3075
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.3046
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2678 - loss: 2.3006
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2662 - loss: 2.2983
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2649 - loss: 2.2967
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2957
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2624 - loss: 2.2940
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2927
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2913
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2907
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2902
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2897
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2892
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.2887
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2570 - loss: 2.2880
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2567 - loss: 2.2874
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2867
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2861
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2856
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2853
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2849
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2845
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2841
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2837
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2833
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2829
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2826
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2822
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2820
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2816
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2813
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2811
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2809
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2806
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2804
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2802
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2799
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2797
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2795
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2795 - val_accuracy: 0.3093 - val_loss: 2.1478
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2186
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2618 - loss: 2.1894  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2495 - loss: 2.2324
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2444 - loss: 2.2483
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2445 - loss: 2.2527
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2451 - loss: 2.2554
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2565
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2474 - loss: 2.2554
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2538
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2500 - loss: 2.2511
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2486
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2516 - loss: 2.2470
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2520 - loss: 2.2461
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2523 - loss: 2.2453
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2526 - loss: 2.2444
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2529 - loss: 2.2437
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2533 - loss: 2.2430
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2423
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2419
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2416
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2412
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2408
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2404
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2402
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2399
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2397
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2396
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2395
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2565 - loss: 2.2394
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2566 - loss: 2.2393
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2392
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2569 - loss: 2.2390
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2571 - loss: 2.2388
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2573 - loss: 2.2387
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2386
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2385
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2576 - loss: 2.2384
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2384
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2383
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2383
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2383
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2383
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2383
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2383 - val_accuracy: 0.3250 - val_loss: 2.1510
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.8680
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1895  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2748 - loss: 2.1921
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2742 - loss: 2.1893
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2747 - loss: 2.1887
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2732 - loss: 2.1912
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.1927
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1930
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1918
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2700 - loss: 2.1911
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2697 - loss: 2.1914
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.1912
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.1907
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2695 - loss: 2.1900
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.1896
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2691 - loss: 2.1895
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2689 - loss: 2.1896
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2687 - loss: 2.1898
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2684 - loss: 2.1902
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2682 - loss: 2.1905
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.1910
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.1914
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2673 - loss: 2.1919
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2671 - loss: 2.1924
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2669 - loss: 2.1928
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2667 - loss: 2.1932
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2665 - loss: 2.1938
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2663 - loss: 2.1942
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2662 - loss: 2.1946
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.1950
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2658 - loss: 2.1956
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2656 - loss: 2.1961
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2654 - loss: 2.1965
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2653 - loss: 2.1968
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2652 - loss: 2.1972
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2651 - loss: 2.1975
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2651 - loss: 2.1979
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.1981
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.1983
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.1985
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2649 - loss: 2.1987
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2649 - loss: 2.1989
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2649 - loss: 2.1991
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2649 - loss: 2.1993
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2649 - loss: 2.1993 - val_accuracy: 0.3349 - val_loss: 2.1333
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1502
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2757  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2433
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2376
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2329
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2311
[1m 152/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2282
[1m 181/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2254
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2233
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2632 - loss: 2.2211
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2638 - loss: 2.2194
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2645 - loss: 2.2173
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2651 - loss: 2.2155
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2657 - loss: 2.2140
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2664 - loss: 2.2123
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.2110
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.2095
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.2084
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2683 - loss: 2.2074
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.2064
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2689 - loss: 2.2055
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2692 - loss: 2.2043
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.2032
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2699 - loss: 2.2023
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.2015
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2009
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2704 - loss: 2.2005
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2000
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1995
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.1991
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.1987
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2712 - loss: 2.1984
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2714 - loss: 2.1980
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 2.1976
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.1972
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.1969
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.1966
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.1963
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2721 - loss: 2.1960
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.1956
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2723 - loss: 2.1953
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2724 - loss: 2.1950
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1947
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1947 - val_accuracy: 0.3171 - val_loss: 2.1212
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.4028
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2789 - loss: 2.2503  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2811 - loss: 2.2349
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2853 - loss: 2.2164
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2871 - loss: 2.2054
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1960
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2904 - loss: 2.1876
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2911 - loss: 2.1836
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1802
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1769
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1735
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1717
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1700
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1684
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1669
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 2.1661
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1653
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2912 - loss: 2.1645
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2910 - loss: 2.1635
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2909 - loss: 2.1626
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2908 - loss: 2.1619
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2906 - loss: 2.1615
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2904 - loss: 2.1611
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2902 - loss: 2.1608
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2901 - loss: 2.1604
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2899 - loss: 2.1602
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1599
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1597
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1595
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1592
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1591
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1588
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1586
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1584
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2887 - loss: 2.1582
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2887 - loss: 2.1580
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2886 - loss: 2.1579
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2886 - loss: 2.1578
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1577
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1576
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1576
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1576
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1576
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1576 - val_accuracy: 0.3327 - val_loss: 2.1516
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9337
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1573  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2744 - loss: 2.1634
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2744 - loss: 2.1745
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2752 - loss: 2.1762
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2754 - loss: 2.1753
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2754 - loss: 2.1747
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2762 - loss: 2.1724
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1708
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1696
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1689
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1681
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1675
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1666
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1657
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1651
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1646
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1640
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1635
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1628
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1620
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1612
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1605
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1597
[1m 644/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1590
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1583
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1577
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1571
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1565
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1559
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1554
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1549
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1544
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1540
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1536
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1533
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1529
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1526
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1523
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1520
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1518
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1515
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1512
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1509
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1507 - val_accuracy: 0.3439 - val_loss: 2.1312
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1348
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3062 - loss: 2.1162  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1180
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1134
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3017 - loss: 2.1072
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3025 - loss: 2.1038
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 2.1033
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3019 - loss: 2.1043
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1066
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2991 - loss: 2.1096
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1118
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 2.1135
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2966 - loss: 2.1152
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1167
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1177
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1183
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1185
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1185
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1183
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1183
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1184
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1184
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1183
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1180
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1178
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1175
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1172
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1167
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1162
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1157
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1152
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1148
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1144
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1141
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2948 - loss: 2.1138
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1135
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1132
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1131
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1129
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1127
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1126
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1124
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1123
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1122 - val_accuracy: 0.3403 - val_loss: 2.0821
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1492
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0816  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3040 - loss: 2.1079
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1086
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1116
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1132
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1118
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1092
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1071
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.1045
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1022
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 2.0996
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.0971
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.0949
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0934
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0923
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3019 - loss: 2.0918
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0916
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0914
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0914
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0914
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0915
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0917
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0919
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0921
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0922
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0922
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0923
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0923
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0923
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0924
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0924
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0926
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0927
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0929
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0930
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0932
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0933
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0934
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0935
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0935
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0936
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0936
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0937 - val_accuracy: 0.3437 - val_loss: 2.0953
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.4605
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3159 - loss: 2.0797  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0975
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0965
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0942
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0904
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0870
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0850
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0825
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0803
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0789
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0773
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0762
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0757
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0753
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0748
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0744
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0740
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0738
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0739
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0742
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0745
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0748
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0751
[1m 644/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0754
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0756
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0760
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0763
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0766
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0767
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0769
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0770
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0771
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0772
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0773
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0775
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0776
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0777
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0777
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0778
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0779
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0780
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0781
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0781 - val_accuracy: 0.3298 - val_loss: 2.1351
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2247
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0508  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0587
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0631
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0658
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 2.0683
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3162 - loss: 2.0698
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3159 - loss: 2.0710
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 2.0718
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0729
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0731
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0728
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0720
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0708
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0701
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0695
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0688
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0679
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0670
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0662
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0653
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0644
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0639
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0634
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0631
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0628
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0624
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0620
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0617
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0615
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0613
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0610
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0608
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0607
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0606
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0604
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0603
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0602
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0601
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0601
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0601
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0602
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0602
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0603
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0603 - val_accuracy: 0.3419 - val_loss: 2.0968
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1567
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2973 - loss: 2.0072  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0022
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3164 - loss: 2.0080
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0123
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0154
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0195
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0227
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0254
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0285
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0308
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0323
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0336
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0349
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0362
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0373
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0382
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0388
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0392
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0396
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0400
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0403
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0406
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0410
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 2.0417
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0422
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0428
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0435
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0441
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0445
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0448
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0451
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0454
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0457
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0459
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0461
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0463
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0464
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0465
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0466
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0466
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0466
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0466
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0466 - val_accuracy: 0.3464 - val_loss: 2.0947
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.5000 - loss: 1.4745
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3692 - loss: 1.9254  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3622 - loss: 1.9322
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3551 - loss: 1.9522
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3509 - loss: 1.9636
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3468 - loss: 1.9732
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9808
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 1.9869
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.9907
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3371 - loss: 1.9938
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3358 - loss: 1.9967
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3346 - loss: 1.9991
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 2.0007
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 2.0024
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3328 - loss: 2.0039
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 2.0048
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3322 - loss: 2.0058
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 2.0069
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0081
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 2.0091
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 2.0100
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0108
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3310 - loss: 2.0114
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3310 - loss: 2.0119
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 2.0123
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3309 - loss: 2.0128
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3308 - loss: 2.0133
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0137
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0141
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0145
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0150
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0154
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0156
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0158
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0159
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0161
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0162
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0163
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0164
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0165
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0166
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0167
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0167
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0167
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0167 - val_accuracy: 0.3570 - val_loss: 2.0825

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 636ms/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:12[0m 854ms/step
[1m 47/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m100/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m157/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 977us/step
[1m214/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 952us/step
[1m272/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 936us/step
[1m326/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 937us/step
[1m381/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 935us/step
[1m436/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 933us/step
[1m491/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 932us/step
[1m541/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 939us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 54/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 951us/step
[1m113/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 899us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 34.03 [%]
Global F1 score (validation) = 32.46 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.02028227 0.0114603  0.01905424 ... 0.06000532 0.03062591 0.01035838]
 [0.00251645 0.00204517 0.00210026 ... 0.0991779  0.00862389 0.00567465]
 [0.00359508 0.00379973 0.00204049 ... 0.00830772 0.00333624 0.00197759]
 ...
 [0.10658535 0.03217422 0.20306078 ... 0.00237673 0.19365835 0.16684347]
 [0.18560559 0.04888822 0.11584105 ... 0.01966846 0.09054137 0.10602071]
 [0.1902519  0.06500384 0.09912143 ... 0.01566058 0.11768898 0.07424483]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 37.38 [%]
Global accuracy score (test) = 26.93 [%]
Global F1 score (train) = 36.02 [%]
Global F1 score (test) = 26.27 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.25      0.43      0.32       184
 CAMINAR CON MÓVIL O LIBRO       0.18      0.18      0.18       184
       CAMINAR USUAL SPEED       0.09      0.04      0.05       184
            CAMINAR ZIGZAG       0.22      0.32      0.26       184
          DE PIE BARRIENDO       0.35      0.27      0.31       184
   DE PIE DOBLANDO TOALLAS       0.43      0.37      0.40       184
    DE PIE MOVIENDO LIBROS       0.31      0.22      0.26       184
          DE PIE USANDO PC       0.11      0.16      0.13       184
        FASE REPOSO CON K5       0.32      0.55      0.40       184
INCREMENTAL CICLOERGOMETRO       0.53      0.39      0.45       184
           SENTADO LEYENDO       0.18      0.15      0.16       184
         SENTADO USANDO PC       0.43      0.05      0.09       184
      SENTADO VIENDO LA TV       0.15      0.23      0.18       184
   SUBIR Y BAJAR ESCALERAS       0.34      0.23      0.28       184
                    TROTAR       0.48      0.48      0.48       161

                  accuracy                           0.27      2737
                 macro avg       0.29      0.27      0.26      2737
              weighted avg       0.29      0.27      0.26      2737


Accuracy capturado en la ejecución 4: 26.93 [%]
F1-score capturado en la ejecución 4: 26.27 [%]

=== EJECUCIÓN 5 ===

--- TRAIN (ejecución 5) ---

--- TEST (ejecución 5) ---
2025-11-07 13:02:27.387852: 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`.
2025-11-07 13:02:27.399541: 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 00:00:1762516947.412693 2764029 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762516947.416819 2764029 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762516947.426517 2764029 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516947.426536 2764029 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516947.426538 2764029 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762516947.426540 2764029 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:02:27.429735: 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 00:00:1762516949.689804 2764029 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762516952.713055 2764159 service.cc:152] XLA service 0x75a424002f00 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762516952.713111 2764159 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:02:32.782943: 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 00:00:1762516953.209885 2764159 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762516955.729005 2764159 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42:46[0m 5s/step - accuracy: 0.1250 - loss: 3.4415
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0743 - loss: 3.4401    
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0685 - loss: 3.4252
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0662 - loss: 3.4100
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0682 - loss: 3.3904
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0710 - loss: 3.3721
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0735 - loss: 3.3563
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0754 - loss: 3.3419
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0772 - loss: 3.3284
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0788 - loss: 3.3147
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0802 - loss: 3.3021
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0817 - loss: 3.2889
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0829 - loss: 3.2780
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0841 - loss: 3.2673
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0854 - loss: 3.2569
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0864 - loss: 3.2482
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0877 - loss: 3.2384
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0888 - loss: 3.2300
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0898 - loss: 3.2223
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0910 - loss: 3.2134
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0922 - loss: 3.2051
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0933 - loss: 3.1969
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0945 - loss: 3.1893
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0955 - loss: 3.1823
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0966 - loss: 3.1754
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0975 - loss: 3.1687
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0985 - loss: 3.1619
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0994 - loss: 3.1560
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1004 - loss: 3.1494
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1014 - loss: 3.1435
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1022 - loss: 3.1380
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1031 - loss: 3.1324
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1040 - loss: 3.1268
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1049 - loss: 3.1213
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1057 - loss: 3.1167
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1065 - loss: 3.1115
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1073 - loss: 3.1068
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1081 - loss: 3.1020
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1088 - loss: 3.0976
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1095 - loss: 3.0931
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1101 - loss: 3.0890
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1108 - loss: 3.0849
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1114 - loss: 3.0812
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1114 - loss: 3.0810 - val_accuracy: 0.2317 - val_loss: 2.4451
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.0625 - loss: 3.4415
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1382 - loss: 2.7053  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1566 - loss: 2.6722
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1655 - loss: 2.6616
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1698 - loss: 2.6562
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1717 - loss: 2.6556
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1732 - loss: 2.6547
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1741 - loss: 2.6542
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1745 - loss: 2.6540
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1745 - loss: 2.6548
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1744 - loss: 2.6562
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1745 - loss: 2.6566
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1748 - loss: 2.6568
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1753 - loss: 2.6565
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1757 - loss: 2.6560
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1763 - loss: 2.6554
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1767 - loss: 2.6550
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1772 - loss: 2.6543
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1776 - loss: 2.6536
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6530
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.6522
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1788 - loss: 2.6513
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1791 - loss: 2.6505
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.6497
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6489
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1801 - loss: 2.6478
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6469
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1806 - loss: 2.6460
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1809 - loss: 2.6450
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1812 - loss: 2.6441
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1814 - loss: 2.6432
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1816 - loss: 2.6425
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1818 - loss: 2.6418
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1820 - loss: 2.6410
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1822 - loss: 2.6402
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6394
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1825 - loss: 2.6387
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6378
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.6369
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1829 - loss: 2.6362
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1830 - loss: 2.6353
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.6344
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1833 - loss: 2.6338 - val_accuracy: 0.2668 - val_loss: 2.3241
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.4985
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1942 - loss: 2.6027  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1918 - loss: 2.6052
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1912 - loss: 2.5953
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1915 - loss: 2.5847
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1931 - loss: 2.5732
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1940 - loss: 2.5657
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1949 - loss: 2.5591
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1959 - loss: 2.5543
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1964 - loss: 2.5515
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1973 - loss: 2.5483
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1983 - loss: 2.5452
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1995 - loss: 2.5424
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2005 - loss: 2.5397
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2015 - loss: 2.5374
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.5354
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5337
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2030 - loss: 2.5321
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2032 - loss: 2.5309
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2035 - loss: 2.5297
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2037 - loss: 2.5282
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2040 - loss: 2.5268
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2041 - loss: 2.5257
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2043 - loss: 2.5246
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2045 - loss: 2.5237
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2046 - loss: 2.5226
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2048 - loss: 2.5216
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2049 - loss: 2.5208
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2051 - loss: 2.5200
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2052 - loss: 2.5192
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2052 - loss: 2.5185
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2054 - loss: 2.5177
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2055 - loss: 2.5170
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2056 - loss: 2.5164
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.5156
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2058 - loss: 2.5149
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2059 - loss: 2.5142
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2061 - loss: 2.5135
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2062 - loss: 2.5127
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2063 - loss: 2.5120
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2065 - loss: 2.5113
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2066 - loss: 2.5105
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2067 - loss: 2.5097
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2067 - loss: 2.5097 - val_accuracy: 0.2742 - val_loss: 2.2741
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2778
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3444  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2264 - loss: 2.3709
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3826
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3882
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2299 - loss: 2.3937
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3996
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2290 - loss: 2.4030
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2284 - loss: 2.4059
[1m 257/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2279 - loss: 2.4083
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2272 - loss: 2.4105
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.4122
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2261 - loss: 2.4136
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2256 - loss: 2.4142
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2254 - loss: 2.4143
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2253 - loss: 2.4142
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2253 - loss: 2.4141
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.4142
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2250 - loss: 2.4143
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2249 - loss: 2.4143
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2248 - loss: 2.4144
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.4145
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2244 - loss: 2.4146
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2242 - loss: 2.4146
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2241 - loss: 2.4145
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2239 - loss: 2.4145
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2238 - loss: 2.4145
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2236 - loss: 2.4146
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.4145
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2234 - loss: 2.4146
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2232 - loss: 2.4145
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2231 - loss: 2.4144
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2231 - loss: 2.4142
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2230 - loss: 2.4141
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.4138
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.4136
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.4134
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.4131
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.4129
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.4126
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.4124
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2228 - loss: 2.4122 - val_accuracy: 0.2887 - val_loss: 2.2016
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.6209
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2064 - loss: 2.3832  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2193 - loss: 2.3822
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2258 - loss: 2.3859
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2285 - loss: 2.3837
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2293 - loss: 2.3815
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2297 - loss: 2.3788
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2300 - loss: 2.3764
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2306 - loss: 2.3735
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2312 - loss: 2.3710
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3684
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3663
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3650
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2324 - loss: 2.3645
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3641
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2326 - loss: 2.3638
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3635
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2331 - loss: 2.3632
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3628
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3626
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2335 - loss: 2.3623
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3621
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3619
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3617
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3615
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.3612
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.3609
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.3606
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3603
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3599
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3595
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3592
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3589
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3586
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3584
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3581
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2345 - loss: 2.3578
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2345 - loss: 2.3575
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3572
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3569
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2347 - loss: 2.3566
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3563
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3561 - val_accuracy: 0.2978 - val_loss: 2.1783
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.5000 - loss: 1.8323
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2799 - loss: 2.3202  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2900
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2648 - loss: 2.2797
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2800
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2822
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2852
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2865
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2874
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2523 - loss: 2.2893
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2916
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2504 - loss: 2.2934
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.2949
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2489 - loss: 2.2958
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2483 - loss: 2.2965
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.2969
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2474 - loss: 2.2973
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2975
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2466 - loss: 2.2978
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2979
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2457 - loss: 2.2981
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2454 - loss: 2.2982
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.2984
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2448 - loss: 2.2986
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2445 - loss: 2.2989
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2442 - loss: 2.2991
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2440 - loss: 2.2993
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2438 - loss: 2.2993
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.2993
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.2993
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.2992
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.2991
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2989
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2987
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2984
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2983
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2982
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2980
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2979
[1m1076/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2977
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2975
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2973
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2971 - val_accuracy: 0.3002 - val_loss: 2.1605
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.1766
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1914  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2852 - loss: 2.2126
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2771 - loss: 2.2297
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2713 - loss: 2.2396
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.2463
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 2.2521
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.2575
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2605
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2627
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2642
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2650
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2651
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2654
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2658
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2661
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2665
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2670
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2675
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2678
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2679
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2680
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2536 - loss: 2.2681
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2681
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2682
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2533 - loss: 2.2681
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2681
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2681
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2681
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2681
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2681
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2680
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2680
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2679
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2533 - loss: 2.2677
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2675
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2673
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2670
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2536 - loss: 2.2668
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2664
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2662
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2659
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2657 - val_accuracy: 0.3051 - val_loss: 2.1706
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1313
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2210 - loss: 2.2649  
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2363 - loss: 2.2437
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2437 - loss: 2.2357
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2322
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2478 - loss: 2.2350
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2367
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2489 - loss: 2.2385
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2403
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.2415
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.2418
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2501 - loss: 2.2415
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2417
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2514 - loss: 2.2416
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2521 - loss: 2.2415
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2526 - loss: 2.2413
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2530 - loss: 2.2412
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2411
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2409
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2407
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2406
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2404
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2402
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2400
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2397
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2395
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2393
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2392
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2391
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2565 - loss: 2.2389
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2567 - loss: 2.2387
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2385
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2569 - loss: 2.2382
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2571 - loss: 2.2378
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2572 - loss: 2.2374
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2573 - loss: 2.2372
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2369
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2366
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2364
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2362
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2576 - loss: 2.2359
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2576 - loss: 2.2357
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2355
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2354 - val_accuracy: 0.3161 - val_loss: 2.1612
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2320
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2025 - loss: 2.2872  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2216 - loss: 2.2692
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2297 - loss: 2.2617
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2354 - loss: 2.2542
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2392 - loss: 2.2498
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2424 - loss: 2.2459
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2448 - loss: 2.2429
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2396
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2366
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2504 - loss: 2.2333
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2518 - loss: 2.2308
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2531 - loss: 2.2286
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2266
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2248
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2231
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2214
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2196
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2179
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2165
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2153
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2142
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2132
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2123
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2115
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2108
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2101
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2093
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2086
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2620 - loss: 2.2077
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2622 - loss: 2.2069
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2624 - loss: 2.2064
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2058
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2052
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2047
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.2042
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2038
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2034
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2638 - loss: 2.2031
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2027
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2641 - loss: 2.2024
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2642 - loss: 2.2022
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2643 - loss: 2.2019
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2644 - loss: 2.2018 - val_accuracy: 0.3175 - val_loss: 2.1258
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3739
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2503  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2365
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2523 - loss: 2.2297
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2260
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2224
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2566 - loss: 2.2205
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2184
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2155
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2136
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2613 - loss: 2.2115
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.2099
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2084
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2070
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2643 - loss: 2.2060
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2647 - loss: 2.2054
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2650 - loss: 2.2046
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2653 - loss: 2.2037
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2656 - loss: 2.2027
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2659 - loss: 2.2018
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2663 - loss: 2.2009
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2666 - loss: 2.2002
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.1994
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2674 - loss: 2.1987
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2677 - loss: 2.1981
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2680 - loss: 2.1975
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.1969
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.1964
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2687 - loss: 2.1959
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2690 - loss: 2.1953
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2692 - loss: 2.1947
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.1940
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.1934
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.1928
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1924
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1920
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.1915
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.1912
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.1907
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.1903
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2714 - loss: 2.1900
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2716 - loss: 2.1896
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.1892
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2718 - loss: 2.1891 - val_accuracy: 0.3226 - val_loss: 2.1064
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.7045
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2104 - loss: 2.3589  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2341 - loss: 2.2941
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2477 - loss: 2.2577
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2394
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2243
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2667 - loss: 2.2137
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2701 - loss: 2.2045
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2720 - loss: 2.1998
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2733 - loss: 2.1968
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1950
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2750 - loss: 2.1930
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1911
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1891
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1876
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2777 - loss: 2.1861
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1845
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1830
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1817
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1804
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1791
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1779
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1769
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1758
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1747
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1738
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1728
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1719
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1711
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1704
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1697
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1691
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1685
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1679
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1675
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1670
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1666
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1662
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1658
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1654
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1650
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1646
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1643 - val_accuracy: 0.3260 - val_loss: 2.1102
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9366
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3011 - loss: 2.0638  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0841
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1007
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1113
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1197
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1245
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1264
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1285
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1304
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1322
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1334
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1347
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1353
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1358
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1362
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1367
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1369
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1369
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1367
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1365
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1365
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1364
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1362
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1359
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1355
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1351
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1348
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1346
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1343
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1341
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1340
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1338
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1335
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1333
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1331
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 2.1328
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 2.1325
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1323
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1321
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1319
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1317
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1315 - val_accuracy: 0.3272 - val_loss: 2.1157
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.4375 - loss: 1.8440
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3290 - loss: 2.0574  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3165 - loss: 2.0654
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0788
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0861
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0909
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0948
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0999
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 2.1029
[1m 254/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3024 - loss: 2.1051
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3023 - loss: 2.1061
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 2.1076
[1m 337/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1084
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1086
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1090
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1091
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1091
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 2.1091
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1090
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1089
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1086
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1083
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1082
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1080
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1078
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1078
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2993 - loss: 2.1077
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1077
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 2.1076
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1075
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1074
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1073
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1072
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2988 - loss: 2.1071
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1071
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 2.1070
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2985 - loss: 2.1070
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1070
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1069
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1068
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1066
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1065
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1064 - val_accuracy: 0.3407 - val_loss: 2.1173
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0508
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2798 - loss: 2.0956  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1046
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2877 - loss: 2.0916
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2948 - loss: 2.0826
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 2.0789
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.0778
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.0772
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.0767
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0764
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0764
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0763
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0760
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0759
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0756
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.0756
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0753
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0751
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0751
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0752
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0752
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0753
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0753
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0753
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0753
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0755
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0756
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0759
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0762
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0764
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0767
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0771
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0775
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0778
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0780
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0783
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0785
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0787
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0788
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0789
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0790
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0791
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0791 - val_accuracy: 0.3173 - val_loss: 2.1206
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3540
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2484 - loss: 2.2331  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2583 - loss: 2.1986
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2686 - loss: 2.1697
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2728 - loss: 2.1584
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2760 - loss: 2.1500
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1411
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1354
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1298
[1m 234/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2875 - loss: 2.1246
[1m 259/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1202
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1157
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1118
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1081
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1055
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1029
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 2.1005
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2971 - loss: 2.0984
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 2.0961
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 2.0945
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 2.0928
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2991 - loss: 2.0914
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 2.0899
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0887
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 2.0875
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0864
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.0855
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 2.0848
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0840
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0833
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0827
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0821
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0815
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0810
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0805
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0800
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0796
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3038 - loss: 2.0792
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0788
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3041 - loss: 2.0785
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0782
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0780
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0777
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0777 - val_accuracy: 0.3456 - val_loss: 2.1272

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 654ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 946us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:09[0m 848ms/step
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m107/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 945us/step
[1m167/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 909us/step
[1m220/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 919us/step
[1m274/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 921us/step
[1m331/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 915us/step
[1m386/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 916us/step
[1m442/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 913us/step
[1m496/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 915us/step
[1m546/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 923us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 48/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m 99/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step
[1m155/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 981us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 35.7 [%]
Global F1 score (validation) = 33.86 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.01861237 0.01595611 0.01106518 ... 0.0264654  0.04327254 0.01356269]
 [0.00197066 0.00161504 0.00050068 ... 0.16755226 0.00541992 0.00350253]
 [0.00040129 0.00020034 0.00108354 ... 0.00215169 0.00038917 0.00073152]
 ...
 [0.13923079 0.06842011 0.19130947 ... 0.00770465 0.19998801 0.07953395]
 [0.19367492 0.06527158 0.13375433 ... 0.0148368  0.15027973 0.06327538]
 [0.19262528 0.04362472 0.16825591 ... 0.00581846 0.16750881 0.08266144]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 39.55 [%]
Global accuracy score (test) = 31.35 [%]
Global F1 score (train) = 38.32 [%]
Global F1 score (test) = 30.13 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.30      0.74      0.43       184
 CAMINAR CON MÓVIL O LIBRO       0.14      0.14      0.14       184
       CAMINAR USUAL SPEED       0.29      0.28      0.28       184
            CAMINAR ZIGZAG       0.31      0.21      0.25       184
          DE PIE BARRIENDO       0.43      0.24      0.31       184
   DE PIE DOBLANDO TOALLAS       0.33      0.32      0.32       184
    DE PIE MOVIENDO LIBROS       0.29      0.18      0.23       184
          DE PIE USANDO PC       0.13      0.08      0.10       184
        FASE REPOSO CON K5       0.39      0.73      0.51       184
INCREMENTAL CICLOERGOMETRO       0.49      0.40      0.44       184
           SENTADO LEYENDO       0.24      0.18      0.21       184
         SENTADO USANDO PC       0.24      0.08      0.12       184
      SENTADO VIENDO LA TV       0.17      0.35      0.23       184
   SUBIR Y BAJAR ESCALERAS       0.40      0.27      0.32       184
                    TROTAR       0.79      0.52      0.62       161

                  accuracy                           0.31      2737
                 macro avg       0.33      0.32      0.30      2737
              weighted avg       0.33      0.31      0.30      2737


Accuracy capturado en la ejecución 5: 31.35 [%]
F1-score capturado en la ejecución 5: 30.13 [%]

=== EJECUCIÓN 6 ===

--- TRAIN (ejecución 6) ---

--- TEST (ejecución 6) ---
2025-11-07 13:03:30.267384: 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`.
2025-11-07 13:03:30.278645: 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 00:00:1762517010.292025 2766733 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517010.296552 2766733 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517010.307198 2766733 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517010.307220 2766733 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517010.307222 2766733 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517010.307224 2766733 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:03:30.310682: 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 00:00:1762517012.553536 2766733 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517015.662751 2766857 service.cc:152] XLA service 0x78cee0030e40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517015.662785 2766857 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:03:35.732358: 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 00:00:1762517016.173860 2766857 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517018.692759 2766857 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:53[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.6168
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0446 - loss: 3.3939        
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0527 - loss: 3.3940
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0567 - loss: 3.3634
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0598 - loss: 3.3438
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0631 - loss: 3.3299
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0665 - loss: 3.3144
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0694 - loss: 3.3008
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0720 - loss: 3.2893
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0740 - loss: 3.2795
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0758 - loss: 3.2708
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0775 - loss: 3.2627
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0792 - loss: 3.2551
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0808 - loss: 3.2480
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0824 - loss: 3.2403
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0837 - loss: 3.2331
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0851 - loss: 3.2256
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0863 - loss: 3.2191
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0875 - loss: 3.2126
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0885 - loss: 3.2068
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0898 - loss: 3.1997
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0910 - loss: 3.1937
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0923 - loss: 3.1867
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0935 - loss: 3.1803
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0945 - loss: 3.1744
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0957 - loss: 3.1681
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0969 - loss: 3.1616
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0981 - loss: 3.1556
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0991 - loss: 3.1504
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1002 - loss: 3.1448
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1013 - loss: 3.1390
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1024 - loss: 3.1334
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1034 - loss: 3.1279
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1042 - loss: 3.1235
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1053 - loss: 3.1178
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1062 - loss: 3.1127
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1072 - loss: 3.1076
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1081 - loss: 3.1027
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1091 - loss: 3.0977
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1099 - loss: 3.0930
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1108 - loss: 3.0884
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1115 - loss: 3.0846
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1122 - loss: 3.0803
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1127 - loss: 3.0777
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1127 - loss: 3.0776 - val_accuracy: 0.2603 - val_loss: 2.3155
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2500 - loss: 2.5333
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2021 - loss: 2.6017  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2042 - loss: 2.6152
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1992 - loss: 2.6257
[1m 117/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1956 - loss: 2.6315
[1m 146/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1943 - loss: 2.6364
[1m 176/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1929 - loss: 2.6414
[1m 206/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1919 - loss: 2.6451
[1m 234/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1913 - loss: 2.6475
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1911 - loss: 2.6480
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1910 - loss: 2.6482
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1909 - loss: 2.6486
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1908 - loss: 2.6487
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1908 - loss: 2.6485
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1907 - loss: 2.6484
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1908 - loss: 2.6484
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1908 - loss: 2.6482
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1909 - loss: 2.6478
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1910 - loss: 2.6473
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1911 - loss: 2.6467
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1911 - loss: 2.6463
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1911 - loss: 2.6460
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1911 - loss: 2.6456
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1911 - loss: 2.6452
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1911 - loss: 2.6448
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1911 - loss: 2.6442
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1911 - loss: 2.6437
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1910 - loss: 2.6431
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1910 - loss: 2.6424
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1909 - loss: 2.6419
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.6413
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.6406
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.6400
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.6393
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1906 - loss: 2.6384
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.6376
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.6367
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.6357
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.6348
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1909 - loss: 2.6339
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1909 - loss: 2.6332
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1910 - loss: 2.6323 - val_accuracy: 0.2813 - val_loss: 2.2232
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1250 - loss: 2.6368
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2328 - loss: 2.4149  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2381 - loss: 2.4059
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2376 - loss: 2.4108
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2353 - loss: 2.4186
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2331 - loss: 2.4246
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2308 - loss: 2.4315
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2285 - loss: 2.4377
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2262 - loss: 2.4434
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2238 - loss: 2.4486
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2215 - loss: 2.4538
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2196 - loss: 2.4579
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4615
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4640
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2153 - loss: 2.4662
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2143 - loss: 2.4681
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2135 - loss: 2.4694
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2127 - loss: 2.4706
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2120 - loss: 2.4718
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2115 - loss: 2.4724
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2111 - loss: 2.4730
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2107 - loss: 2.4735
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2104 - loss: 2.4739
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2102 - loss: 2.4743
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2100 - loss: 2.4746
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2098 - loss: 2.4749
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2096 - loss: 2.4751
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2094 - loss: 2.4752
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2092 - loss: 2.4754
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2090 - loss: 2.4755
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2089 - loss: 2.4756
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2087 - loss: 2.4757
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2086 - loss: 2.4758
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2084 - loss: 2.4758
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2083 - loss: 2.4759
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4760
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2081 - loss: 2.4761
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2080 - loss: 2.4761
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2079 - loss: 2.4762
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2078 - loss: 2.4762
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2077 - loss: 2.4763
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2076 - loss: 2.4763
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.4763
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2075 - loss: 2.4763 - val_accuracy: 0.2990 - val_loss: 2.1805
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.5011
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2345 - loss: 2.3815  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2360 - loss: 2.3710
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2324 - loss: 2.3776
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2299 - loss: 2.3832
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2283 - loss: 2.3870
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.3912
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2250 - loss: 2.3935
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2240 - loss: 2.3947
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2228 - loss: 2.3960
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3965
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2216 - loss: 2.3974
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2210 - loss: 2.3982
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2205 - loss: 2.3988
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.3995
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2196 - loss: 2.4003
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2190 - loss: 2.4011
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4021
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4028
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4034
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2174 - loss: 2.4037
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4039
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4041
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2167 - loss: 2.4043
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4042
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4041
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4040
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4039
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4038
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4037
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4036
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4034
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4032
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4030
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4028
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4027
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4025
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4024
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4024
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4023
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4023
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4022
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4021
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4021 - val_accuracy: 0.3244 - val_loss: 2.1590
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.1650
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1822 - loss: 2.4099  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2049 - loss: 2.3894
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2114 - loss: 2.3826
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2158 - loss: 2.3755
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2184 - loss: 2.3728
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2200 - loss: 2.3698
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2219 - loss: 2.3680
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2233 - loss: 2.3676
[1m 254/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2245 - loss: 2.3675
[1m 283/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3674
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2262 - loss: 2.3672
[1m 337/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2268 - loss: 2.3666
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2273 - loss: 2.3659
[1m 393/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2276 - loss: 2.3653
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3650
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2281 - loss: 2.3648
[1m 476/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2282 - loss: 2.3645
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2283 - loss: 2.3643
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2284 - loss: 2.3639
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2285 - loss: 2.3634
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3627
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3619
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3612
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2292 - loss: 2.3605
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3596
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3588
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2298 - loss: 2.3581
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2300 - loss: 2.3573
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2302 - loss: 2.3568
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2303 - loss: 2.3562
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2305 - loss: 2.3557
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2306 - loss: 2.3552
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2308 - loss: 2.3547
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2309 - loss: 2.3542
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2311 - loss: 2.3537
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2313 - loss: 2.3532
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2314 - loss: 2.3528
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3523
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3519
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3514
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3509
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3507 - val_accuracy: 0.3315 - val_loss: 2.1299
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.4813
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2225 - loss: 2.3344  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2240 - loss: 2.3377
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2249 - loss: 2.3377
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3349
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2302 - loss: 2.3332
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2308 - loss: 2.3323
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3307
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3279
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2340 - loss: 2.3261
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3248
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2352 - loss: 2.3236
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2357 - loss: 2.3226
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.3218
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2362 - loss: 2.3212
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.3206
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2366 - loss: 2.3198
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2368 - loss: 2.3191
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2370 - loss: 2.3185
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.3179
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2375 - loss: 2.3172
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.3166
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3161
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2381 - loss: 2.3155
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2383 - loss: 2.3149
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2385 - loss: 2.3144
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2387 - loss: 2.3140
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2388 - loss: 2.3136
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2390 - loss: 2.3133
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2391 - loss: 2.3129
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2392 - loss: 2.3126
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2393 - loss: 2.3123
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2395 - loss: 2.3119
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2396 - loss: 2.3114
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2397 - loss: 2.3110
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2399 - loss: 2.3107
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2400 - loss: 2.3102
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2401 - loss: 2.3098
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2402 - loss: 2.3093
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2403 - loss: 2.3089
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2404 - loss: 2.3086
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2405 - loss: 2.3083
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2406 - loss: 2.3079
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2406 - loss: 2.3079 - val_accuracy: 0.3317 - val_loss: 2.1233
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.2500 - loss: 2.6481
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2078 - loss: 2.3632  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2224 - loss: 2.3340
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2253 - loss: 2.3263
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3208
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3125
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3040
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2344 - loss: 2.2979
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2362 - loss: 2.2936
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2371 - loss: 2.2912
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.2886
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2391 - loss: 2.2865
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2398 - loss: 2.2850
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2406 - loss: 2.2836
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2413 - loss: 2.2825
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2420 - loss: 2.2815
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2806
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2797
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2438 - loss: 2.2789
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2441 - loss: 2.2781
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2445 - loss: 2.2774
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2448 - loss: 2.2767
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.2760
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2453 - loss: 2.2753
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2748
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2457 - loss: 2.2742
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2459 - loss: 2.2737
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.2732
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2728
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.2723
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2719
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2715
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2711
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2709
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2474 - loss: 2.2705
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2475 - loss: 2.2702
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2477 - loss: 2.2699
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2478 - loss: 2.2696
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2693
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2481 - loss: 2.2690
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2482 - loss: 2.2687
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2484 - loss: 2.2684
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2681
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2680 - val_accuracy: 0.3506 - val_loss: 2.1006
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0547
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2343 - loss: 2.2448  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2377 - loss: 2.2576
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2419 - loss: 2.2541
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2446 - loss: 2.2484
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2481 - loss: 2.2429
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2387
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2527 - loss: 2.2370
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2364
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2369
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2365
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2362
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2361
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2362
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2572 - loss: 2.2363
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2366
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2370
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2374
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2377
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2378
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2580 - loss: 2.2375
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2372
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2370
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2368
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2369
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2370
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2370
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2371
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2372
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2371
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2586 - loss: 2.2369
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2367
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2365
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2362
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2359
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2357
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2355
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2354
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2352
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2350
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2348
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2346
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2344
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2342
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2342 - val_accuracy: 0.3407 - val_loss: 2.1024
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.6793
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2012 - loss: 2.3670  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.3091
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2328 - loss: 2.2909
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.2778
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2423 - loss: 2.2679
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.2601
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2473 - loss: 2.2546
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2489 - loss: 2.2517
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2501 - loss: 2.2502
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2494
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2517 - loss: 2.2485
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2524 - loss: 2.2473
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2529 - loss: 2.2463
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2533 - loss: 2.2455
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2444
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2431
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2416
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2402
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2390
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2379
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2370
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2361
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2565 - loss: 2.2352
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2567 - loss: 2.2344
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2569 - loss: 2.2337
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2571 - loss: 2.2331
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2572 - loss: 2.2327
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2323
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2319
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2316
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2313
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2310
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2307
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2303
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2300
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2296
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2293
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2289
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2285
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2282
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2278
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2275
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2275 - val_accuracy: 0.3367 - val_loss: 2.1028
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4764
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2632 - loss: 2.1222  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2659 - loss: 2.1399
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2679 - loss: 2.1477
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2675 - loss: 2.1525
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2666 - loss: 2.1598
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2659 - loss: 2.1652
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 2.1684
[1m 207/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2653 - loss: 2.1695
[1m 234/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 2.1707
[1m 260/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2656 - loss: 2.1719
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2657 - loss: 2.1732
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2660 - loss: 2.1736
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2664 - loss: 2.1738
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2668 - loss: 2.1740
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.1745
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.1747
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.1752
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2683 - loss: 2.1754
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.1756
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.1757
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2690 - loss: 2.1758
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2692 - loss: 2.1757
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.1758
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2694 - loss: 2.1758
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.1759
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.1759
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.1759
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.1759
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.1759
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1760
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1761
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1761
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1761
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1762
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.1762
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1762
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.1762
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.1762
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2712 - loss: 2.1762
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.1762
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.1762
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2714 - loss: 2.1763
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 2.1763
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2715 - loss: 2.1763 - val_accuracy: 0.3528 - val_loss: 2.1096
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2587
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1486  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1439
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1377
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2880 - loss: 2.1367
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2886 - loss: 2.1369
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1341
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2901 - loss: 2.1314
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2904 - loss: 2.1314
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2904 - loss: 2.1318
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1329
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1337
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1343
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2886 - loss: 2.1352
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1358
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1365
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2880 - loss: 2.1371
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1375
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1380
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2874 - loss: 2.1387
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1393
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1399
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1406
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1412
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1418
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1424
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1431
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1437
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1443
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1448
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1453
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1457
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1461
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1464
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1467
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1470
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1472
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1474
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1476
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1478
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1479
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1480
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1481
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1482
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1483 - val_accuracy: 0.3439 - val_loss: 2.1147
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2500 - loss: 2.3047
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2591 - loss: 2.1384  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2641 - loss: 2.1527
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2686 - loss: 2.1585
[1m  99/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2696 - loss: 2.1615
[1m 127/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2720 - loss: 2.1637
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1627
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2759 - loss: 2.1599
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2775 - loss: 2.1574
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1548
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1537
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1523
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1511
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1498
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1488
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1479
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1473
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1466
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1461
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1458
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1454
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1449
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1443
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1438
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1434
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1431
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1428
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1425
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1422
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1420
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1418
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1416
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1416
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1415
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1414
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1413
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1411
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1410
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1408
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1407
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1404
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1402
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1400
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1398 - val_accuracy: 0.3435 - val_loss: 2.1050

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 633ms/step
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:08[0m 847ms/step
[1m 53/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 966us/step  
[1m111/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 913us/step
[1m166/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 917us/step
[1m226/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 895us/step
[1m282/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 896us/step
[1m341/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 888us/step
[1m400/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 883us/step
[1m454/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 888us/step
[1m514/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 882us/step
[1m574/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 879us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m56/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 915us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 55/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 940us/step
[1m110/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 927us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 34.56 [%]
Global F1 score (validation) = 32.62 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.02767384 0.01208448 0.01166582 ... 0.01463997 0.05184793 0.01328425]
 [0.00124295 0.00214867 0.00047427 ... 0.19179957 0.00255436 0.00131183]
 [0.00037207 0.00053473 0.00075741 ... 0.00282789 0.00084687 0.00099445]
 ...
 [0.06911249 0.04551638 0.21843171 ... 0.00270558 0.20224147 0.17553258]
 [0.14953664 0.0375743  0.13986279 ... 0.00759848 0.10997406 0.20267452]
 [0.08040036 0.04172121 0.2014736  ... 0.00261199 0.2217705  0.16439313]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 37.57 [%]
Global accuracy score (test) = 27.77 [%]
Global F1 score (train) = 35.72 [%]
Global F1 score (test) = 25.67 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.26      0.46      0.33       184
 CAMINAR CON MÓVIL O LIBRO       0.22      0.18      0.20       184
       CAMINAR USUAL SPEED       0.19      0.17      0.18       184
            CAMINAR ZIGZAG       0.24      0.19      0.21       184
          DE PIE BARRIENDO       0.46      0.14      0.21       184
   DE PIE DOBLANDO TOALLAS       0.26      0.34      0.29       184
    DE PIE MOVIENDO LIBROS       0.24      0.22      0.23       184
          DE PIE USANDO PC       0.11      0.05      0.07       184
        FASE REPOSO CON K5       0.36      0.73      0.49       184
INCREMENTAL CICLOERGOMETRO       0.43      0.50      0.46       184
           SENTADO LEYENDO       0.19      0.14      0.16       184
         SENTADO USANDO PC       0.11      0.02      0.04       184
      SENTADO VIENDO LA TV       0.18      0.27      0.22       184
   SUBIR Y BAJAR ESCALERAS       0.22      0.25      0.24       184
                    TROTAR       0.52      0.55      0.53       161

                  accuracy                           0.28      2737
                 macro avg       0.27      0.28      0.26      2737
              weighted avg       0.26      0.28      0.25      2737


Accuracy capturado en la ejecución 6: 27.77 [%]
F1-score capturado en la ejecución 6: 25.67 [%]

=== EJECUCIÓN 7 ===

--- TRAIN (ejecución 7) ---

--- TEST (ejecución 7) ---
2025-11-07 13:04:25.959793: 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`.
2025-11-07 13:04:25.971365: 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 00:00:1762517065.984675 2769108 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517065.988802 2769108 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517065.998576 2769108 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517065.998594 2769108 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517065.998596 2769108 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517065.998598 2769108 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:04:26.001799: 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 00:00:1762517068.250651 2769108 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517071.298702 2769239 service.cc:152] XLA service 0x7c741801b8a0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517071.298754 2769239 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:04:31.370028: 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 00:00:1762517071.811337 2769239 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517074.352141 2769239 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43:51[0m 5s/step - accuracy: 0.0625 - loss: 3.7135
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0789 - loss: 3.4580    
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0752 - loss: 3.4016
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0712 - loss: 3.3729
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0705 - loss: 3.3541
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0726 - loss: 3.3314
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0745 - loss: 3.3153
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0761 - loss: 3.3007
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0778 - loss: 3.2880
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0792 - loss: 3.2775
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0808 - loss: 3.2675
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0822 - loss: 3.2586
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0835 - loss: 3.2500
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0848 - loss: 3.2411
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0861 - loss: 3.2323
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0872 - loss: 3.2243
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0884 - loss: 3.2163
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0895 - loss: 3.2085
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0907 - loss: 3.2012
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0918 - loss: 3.1944
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0929 - loss: 3.1873
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0940 - loss: 3.1811
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0949 - loss: 3.1749
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0959 - loss: 3.1687
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0969 - loss: 3.1626
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0977 - loss: 3.1574
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0987 - loss: 3.1515
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0995 - loss: 3.1462
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1004 - loss: 3.1408
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1012 - loss: 3.1356
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1020 - loss: 3.1306
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1028 - loss: 3.1257
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1035 - loss: 3.1214
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1043 - loss: 3.1168
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1050 - loss: 3.1126
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1058 - loss: 3.1081
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1066 - loss: 3.1035
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1072 - loss: 3.0999
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1080 - loss: 3.0956
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1087 - loss: 3.0916
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1095 - loss: 3.0875
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1102 - loss: 3.0833
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1110 - loss: 3.0791
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1110 - loss: 3.0790
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1110 - loss: 3.0788 - val_accuracy: 0.2237 - val_loss: 2.4327
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.3769
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2004 - loss: 2.6765  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1965 - loss: 2.6628
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1900 - loss: 2.6708
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6803
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1841 - loss: 2.6850
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6874
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.6875
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1809 - loss: 2.6883
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1802 - loss: 2.6893
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1798 - loss: 2.6897
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6895
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1793 - loss: 2.6895
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1791 - loss: 2.6892
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1787 - loss: 2.6890
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.6889
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1782 - loss: 2.6886
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6882
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6876
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6869
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6861
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6853
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6843
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6833
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6823
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6812
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6800
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6789
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1782 - loss: 2.6778
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1783 - loss: 2.6767
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1784 - loss: 2.6755
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1784 - loss: 2.6745
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1785 - loss: 2.6733
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1786 - loss: 2.6722
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1786 - loss: 2.6711
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1787 - loss: 2.6700
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1788 - loss: 2.6688
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1789 - loss: 2.6677
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1790 - loss: 2.6666
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1791 - loss: 2.6656
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.6644
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.6633
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6624 - val_accuracy: 0.2478 - val_loss: 2.3147
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.6006
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2215 - loss: 2.5392  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2207 - loss: 2.5231
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2162 - loss: 2.5186
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2135 - loss: 2.5147
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2117 - loss: 2.5120
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2107 - loss: 2.5106
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.5104
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2087 - loss: 2.5092
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2082 - loss: 2.5090
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2076 - loss: 2.5099
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2070 - loss: 2.5108
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2065 - loss: 2.5110
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2060 - loss: 2.5121
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2055 - loss: 2.5128
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2051 - loss: 2.5135
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2047 - loss: 2.5141
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2044 - loss: 2.5145
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2041 - loss: 2.5150
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2038 - loss: 2.5154
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2036 - loss: 2.5157
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2035 - loss: 2.5160
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2033 - loss: 2.5159
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2032 - loss: 2.5159
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2031 - loss: 2.5157
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2030 - loss: 2.5155
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2030 - loss: 2.5153
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2029 - loss: 2.5150
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2028 - loss: 2.5148
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2027 - loss: 2.5146
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2027 - loss: 2.5143
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5141
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5139
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5136
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5133
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5129
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5126
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5123
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5120
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5117
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5114
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5110
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5107
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2027 - loss: 2.5104 - val_accuracy: 0.2754 - val_loss: 2.2334
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.1206
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2525 - loss: 2.3131  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2309 - loss: 2.3554
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2250 - loss: 2.3747
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2238 - loss: 2.3860
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3931
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2209 - loss: 2.3978
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2199 - loss: 2.4014
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4043
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4062
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4074
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4091
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2175 - loss: 2.4103
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2173 - loss: 2.4116
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4131
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4145
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2172 - loss: 2.4153
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2173 - loss: 2.4157
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2174 - loss: 2.4159
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2175 - loss: 2.4163
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4169
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4173
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4177
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4181
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4185
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4189
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4192
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4194
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4197
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4200
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4201
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2179 - loss: 2.4203
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2179 - loss: 2.4204
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4205
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4205
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4205
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4205
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4205
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2181 - loss: 2.4204
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4203
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4202
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4201
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4200
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4199 - val_accuracy: 0.3020 - val_loss: 2.1902
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3462
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2785 - loss: 2.3669  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2584 - loss: 2.3687
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2477 - loss: 2.3776
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3811
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2370 - loss: 2.3832
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3851
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3863
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3869
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2294 - loss: 2.3868
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3861
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2281 - loss: 2.3854
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2278 - loss: 2.3846
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2274 - loss: 2.3844
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2272 - loss: 2.3842
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2269 - loss: 2.3840
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2267 - loss: 2.3839
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.3836
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.3831
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.3824
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2267 - loss: 2.3817
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2268 - loss: 2.3811
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2268 - loss: 2.3807
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3803
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2271 - loss: 2.3799
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2273 - loss: 2.3794
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2275 - loss: 2.3789
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2277 - loss: 2.3784
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3780
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2281 - loss: 2.3776
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2282 - loss: 2.3773
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2283 - loss: 2.3770
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2284 - loss: 2.3767
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2285 - loss: 2.3763
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3760
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3757
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3754
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3750
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3747
[1m1076/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3745
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3742
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3739
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3737 - val_accuracy: 0.3081 - val_loss: 2.1543
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.3414
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2328 - loss: 2.4466  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2339 - loss: 2.4063
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2311 - loss: 2.3911
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2297 - loss: 2.3825
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2291 - loss: 2.3773
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2285 - loss: 2.3722
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2281 - loss: 2.3672
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2276 - loss: 2.3641
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2275 - loss: 2.3611
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2278 - loss: 2.3584
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2282 - loss: 2.3556
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3528
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2291 - loss: 2.3507
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3487
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2302 - loss: 2.3468
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2307 - loss: 2.3453
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2312 - loss: 2.3436
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3422
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3406
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3393
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3382
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2327 - loss: 2.3374
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3367
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3362
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3357
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3354
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3350
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3346
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3343
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3339
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.3336
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3332
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3330
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3327
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3324
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3321
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3319
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2345 - loss: 2.3316
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3314
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2347 - loss: 2.3311
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3309
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3306 - val_accuracy: 0.3043 - val_loss: 2.1464
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m33s[0m 29ms/step - accuracy: 0.1875 - loss: 1.9737
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2072 - loss: 2.3852  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2147 - loss: 2.3675
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2210 - loss: 2.3572
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2262 - loss: 2.3468
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2298 - loss: 2.3372
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3296
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2335 - loss: 2.3253
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2350 - loss: 2.3209
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2359 - loss: 2.3180
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.3141
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2383 - loss: 2.3108
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2391 - loss: 2.3080
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2397 - loss: 2.3055
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2403 - loss: 2.3030
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2408 - loss: 2.3010
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2411 - loss: 2.2998
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2414 - loss: 2.2987
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2416 - loss: 2.2978
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2418 - loss: 2.2970
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.2962
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2420 - loss: 2.2955
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2421 - loss: 2.2947
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2422 - loss: 2.2941
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2423 - loss: 2.2936
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2423 - loss: 2.2931
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2424 - loss: 2.2927
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2424 - loss: 2.2923
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.2918
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2426 - loss: 2.2912
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2906
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2902
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2429 - loss: 2.2897
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.2892
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.2888
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2883
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2879
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.2874
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.2870
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.2867
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2437 - loss: 2.2864
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2438 - loss: 2.2861
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2438 - loss: 2.2859 - val_accuracy: 0.3178 - val_loss: 2.1618
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.5000 - loss: 2.0282
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3026 - loss: 2.1532  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1816
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1970
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2708 - loss: 2.2102
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2667 - loss: 2.2202
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2647 - loss: 2.2257
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2305
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2329
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2613 - loss: 2.2340
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2351
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2359
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2366
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2374
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2380
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2387
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2392
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2397
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2399
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2404
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2409
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2413
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2416
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2417
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2416
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2414
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2412
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2411
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2410
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2408
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2407
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2405
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2402
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2400
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2399
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2398
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2396
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2395
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2394
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2393
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2392
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2392
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2392
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2392 - val_accuracy: 0.3238 - val_loss: 2.1271
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0829
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2406  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2442 - loss: 2.2533
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2414 - loss: 2.2612
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2415 - loss: 2.2606
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2438 - loss: 2.2571
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2449 - loss: 2.2574
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2456 - loss: 2.2589
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2597
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2602
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2604
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2604
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2475 - loss: 2.2602
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.2597
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2482 - loss: 2.2590
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2584
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2578
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2570
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.2560
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2549
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2503 - loss: 2.2539
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2506 - loss: 2.2530
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.2522
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2512
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2514 - loss: 2.2502
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2517 - loss: 2.2492
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2520 - loss: 2.2482
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2523 - loss: 2.2472
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2527 - loss: 2.2462
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2530 - loss: 2.2453
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2445
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2438
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2431
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2424
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2416
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2410
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2403
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2397
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2392
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2386
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2381
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2377
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2372
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2371 - val_accuracy: 0.3343 - val_loss: 2.1077
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1011
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2469 - loss: 2.1804  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2638 - loss: 2.1714
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2713 - loss: 2.1702
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2742 - loss: 2.1750
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1756
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1757
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1771
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1784
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1792
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1794
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1791
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1790
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1788
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1785
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1785
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1786
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1787
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1788
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1789
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1790
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1792
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1793
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1795
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1797
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1798
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1799
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1799
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1800
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1801
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1802
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1803
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1804
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1804
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1805
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1805
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1806
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1807
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1808
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1810
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1811
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1812
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1813
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1813 - val_accuracy: 0.3417 - val_loss: 2.1078
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.4016
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2178 - loss: 2.3269  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2279 - loss: 2.2930
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2328 - loss: 2.2737
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.2600
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2493
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2465 - loss: 2.2410
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2504 - loss: 2.2329
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2529 - loss: 2.2272
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2210
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2166
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2124
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2089
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2624 - loss: 2.2054
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2030
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 2.2011
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2648 - loss: 2.1993
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 2.1975
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2659 - loss: 2.1961
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2664 - loss: 2.1947
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2669 - loss: 2.1935
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2673 - loss: 2.1926
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.1919
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2680 - loss: 2.1911
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2684 - loss: 2.1904
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2687 - loss: 2.1897
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2690 - loss: 2.1892
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2693 - loss: 2.1887
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2696 - loss: 2.1882
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.1876
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.1873
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1870
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1867
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1863
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1860
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1857
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.1854
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.1851
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.1847
[1m1076/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 2.1844
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2716 - loss: 2.1840
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.1837
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2719 - loss: 2.1834 - val_accuracy: 0.3417 - val_loss: 2.0847
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.3619
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3141 - loss: 2.1535  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3035 - loss: 2.1523
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1529
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1496
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 2.1494
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1493
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1497
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1502
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1497
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1498
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1498
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1498
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1498
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1494
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1490
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1486
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1480
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1472
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1462
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1452
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1444
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1439
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1436
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1433
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1430
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1428
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2938 - loss: 2.1427
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1426
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1425
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1424
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 2.1422
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1421
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1419
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1419
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1418
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1418
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1418
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2917 - loss: 2.1418
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2916 - loss: 2.1418
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2915 - loss: 2.1418
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1417
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1417
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1417 - val_accuracy: 0.3425 - val_loss: 2.0704
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1250 - loss: 2.1039
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3003 - loss: 2.0552  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0652
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0627
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0648
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0662
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0674
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0711
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0750
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0777
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0794
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0806
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0814
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0820
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0829
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0837
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0843
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0846
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0850
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0853
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0858
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0863
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0868
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0876
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0884
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0892
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0900
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3081 - loss: 2.0908
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0915
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3074 - loss: 2.0922
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0927
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3067 - loss: 2.0933
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0938
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0943
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0949
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0953
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0957
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0961
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3049 - loss: 2.0965
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0970
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0974
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0979
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3040 - loss: 2.0984
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0986 - val_accuracy: 0.3492 - val_loss: 2.0937
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2500 - loss: 2.5559
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1941  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2971 - loss: 2.1560
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3034 - loss: 2.1278
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3071 - loss: 2.1121
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 2.1024
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0951
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0905
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0878
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0863
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0854
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0853
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0855
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0857
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0857
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0860
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0863
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0868
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0873
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0878
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0882
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0885
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0889
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0893
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0895
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0899
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0901
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0904
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0907
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3084 - loss: 2.0909
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3083 - loss: 2.0911
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3082 - loss: 2.0913
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3081 - loss: 2.0914
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0915
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3079 - loss: 2.0917
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3079 - loss: 2.0918
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3078 - loss: 2.0919
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3078 - loss: 2.0920
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0922
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3076 - loss: 2.0924
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0925
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0927
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3074 - loss: 2.0928
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3073 - loss: 2.0929 - val_accuracy: 0.3433 - val_loss: 2.0715
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.8851
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2728 - loss: 2.1150  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1018
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1024
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1058
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1076
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2948 - loss: 2.1059
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1027
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 2.0998
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0966
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0943
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0923
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0910
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0902
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0895
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0885
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0879
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0875
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0871
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0867
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0865
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0863
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0862
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0860
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0860
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0861
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0861
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0863
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 2.0864
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 2.0866
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0866
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0867
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0868
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0870
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0871
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0872
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0872
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0873
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0873
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0873
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0873
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0873
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0873
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0873 - val_accuracy: 0.3619 - val_loss: 2.0683
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.2580
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0796  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2954 - loss: 2.0691
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2945 - loss: 2.0699
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2962 - loss: 2.0711
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 2.0734
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 2.0755
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 2.0768
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 2.0774
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.0781
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 2.0787
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 2.0789
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0789
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.0787
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0786
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 2.0784
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.0783
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0781
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3019 - loss: 2.0779
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0773
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0768
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0763
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3033 - loss: 2.0760
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0758
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3038 - loss: 2.0756
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3040 - loss: 2.0754
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0752
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0750
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0748
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3049 - loss: 2.0745
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0743
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0740
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0738
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0735
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0732
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0730
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0728
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0727
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0726
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0725
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3067 - loss: 2.0724
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0723
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0722
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0722 - val_accuracy: 0.3407 - val_loss: 2.0517
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.5000 - loss: 1.6299
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0560  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0523
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3187 - loss: 2.0522
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0477
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0465
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0466
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0452
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0434
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0410
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0389
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0368
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0349
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0341
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0338
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0337
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0341
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0344
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0345
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0346
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0348
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0352
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0357
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0363
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0368
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0372
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0375
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0380
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0385
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0389
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0393
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0398
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0402
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0405
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0409
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0413
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0415
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0418
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0422
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0426
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0428
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 2.0431
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 2.0434
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3190 - loss: 2.0435 - val_accuracy: 0.3443 - val_loss: 2.0882
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0009
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0282  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0195
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0234
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0292
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0329
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 2.0355
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0362
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0366
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0370
[1m 284/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0373
[1m 312/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0375
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0378
[1m 366/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0380
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0380
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0380
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0378
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0376
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0375
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0374
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0373
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0372
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0370
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0368
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0368
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0367
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0365
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0362
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0361
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0359
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0357
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0356
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0356
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0356
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0356
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0356
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0355
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0354
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0353
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3177 - loss: 2.0352
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0351
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0351
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0350 - val_accuracy: 0.3431 - val_loss: 2.0561
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1217
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3612 - loss: 1.9873  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3480 - loss: 2.0022
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3484 - loss: 2.0071
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3483 - loss: 2.0092
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3475 - loss: 2.0092
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3462 - loss: 2.0086
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3455 - loss: 2.0074
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 2.0065
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3445 - loss: 2.0060
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3441 - loss: 2.0051
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 2.0045
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 2.0042
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3429 - loss: 2.0042
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3423 - loss: 2.0043
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3415 - loss: 2.0045
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3409 - loss: 2.0048
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 2.0050
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 2.0053
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 2.0054
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3388 - loss: 2.0057
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3383 - loss: 2.0061
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 2.0064
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3375 - loss: 2.0067
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 2.0070
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 2.0073
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3367 - loss: 2.0077
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 2.0082
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 2.0086
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 2.0090
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3357 - loss: 2.0093
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3355 - loss: 2.0095
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3354 - loss: 2.0097
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3352 - loss: 2.0099
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3351 - loss: 2.0100
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3349 - loss: 2.0100
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3348 - loss: 2.0101
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3347 - loss: 2.0101
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3346 - loss: 2.0101
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3345 - loss: 2.0102
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3344 - loss: 2.0102
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3343 - loss: 2.0102
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3342 - loss: 2.0103
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3342 - loss: 2.0104 - val_accuracy: 0.3663 - val_loss: 2.0582
Epoch 20/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.4375 - loss: 1.7366
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3686 - loss: 1.8917  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3470 - loss: 1.9421
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3405 - loss: 1.9623
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3359 - loss: 1.9733
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3322 - loss: 1.9819
[1m 153/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3295 - loss: 1.9895
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3286 - loss: 1.9934
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3284 - loss: 1.9953
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 1.9963
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 1.9970
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 1.9979
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3300 - loss: 1.9985
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3302 - loss: 1.9988
[1m 366/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 1.9988
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 1.9988
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3308 - loss: 1.9990
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3308 - loss: 1.9991
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3308 - loss: 1.9994
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 1.9996
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 1.9997
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 1.9997
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0000
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0003
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0005
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0009
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0014
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0017
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0020
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0023
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0024
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0026
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0027
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3308 - loss: 2.0028
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3308 - loss: 2.0030
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3309 - loss: 2.0030
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 2.0030
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0030
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3312 - loss: 2.0030
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3314 - loss: 2.0029
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 2.0028
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0027
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3317 - loss: 2.0026
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3318 - loss: 2.0025
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3318 - loss: 2.0025 - val_accuracy: 0.3609 - val_loss: 2.0660
Epoch 21/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.0419
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3296 - loss: 1.9569  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3334 - loss: 1.9610
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3366 - loss: 1.9609
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.9579
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9568
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3386 - loss: 1.9564
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3386 - loss: 1.9564
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3382 - loss: 1.9573
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3381 - loss: 1.9580
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9591
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3378 - loss: 1.9602
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3377 - loss: 1.9616
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3376 - loss: 1.9628
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3374 - loss: 1.9640
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3373 - loss: 1.9651
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3372 - loss: 1.9660
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3371 - loss: 1.9669
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3369 - loss: 1.9677
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3368 - loss: 1.9685
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.9694
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3364 - loss: 1.9704
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.9712
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.9717
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.9721
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.9724
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3365 - loss: 1.9728
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3366 - loss: 1.9731
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3367 - loss: 1.9733
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3368 - loss: 1.9735
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3369 - loss: 1.9737
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.9738
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.9739
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3373 - loss: 1.9739
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3374 - loss: 1.9740
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.9741
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.9743
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.9744
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.9745
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.9746
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3378 - loss: 1.9746
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9747
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9748
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9748 - val_accuracy: 0.3558 - val_loss: 2.0803

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 648ms/step
[1m45/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:59[0m 831ms/step
[1m 54/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 958us/step  
[1m108/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 944us/step
[1m163/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 934us/step
[1m217/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 936us/step
[1m269/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 943us/step
[1m325/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 936us/step
[1m377/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 942us/step
[1m428/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 947us/step
[1m485/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 940us/step
[1m538/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 941us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 54/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 950us/step
[1m113/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 899us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 34.35 [%]
Global F1 score (validation) = 33.3 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.01676441 0.01463143 0.01201759 ... 0.04833589 0.01949743 0.00778757]
 [0.00717096 0.00463031 0.0068066  ... 0.14691141 0.01167797 0.00516758]
 [0.00198586 0.00170348 0.00094436 ... 0.00508589 0.00296892 0.00144282]
 ...
 [0.16744499 0.06355511 0.19707662 ... 0.00527029 0.17643571 0.0982486 ]
 [0.22079901 0.08999348 0.12410236 ... 0.01573296 0.14235884 0.07580896]
 [0.18816441 0.07678552 0.17115809 ... 0.00528501 0.1674447  0.08888875]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 34.73 [%]
Global accuracy score (test) = 27.66 [%]
Global F1 score (train) = 33.76 [%]
Global F1 score (test) = 26.8 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.22      0.58      0.32       184
 CAMINAR CON MÓVIL O LIBRO       0.12      0.10      0.11       184
       CAMINAR USUAL SPEED       0.06      0.03      0.04       184
            CAMINAR ZIGZAG       0.24      0.16      0.19       184
          DE PIE BARRIENDO       0.40      0.24      0.30       184
   DE PIE DOBLANDO TOALLAS       0.25      0.30      0.27       184
    DE PIE MOVIENDO LIBROS       0.24      0.21      0.22       184
          DE PIE USANDO PC       0.20      0.15      0.17       184
        FASE REPOSO CON K5       0.41      0.57      0.47       184
INCREMENTAL CICLOERGOMETRO       0.44      0.46      0.45       184
           SENTADO LEYENDO       0.24      0.23      0.23       184
         SENTADO USANDO PC       0.19      0.09      0.12       184
      SENTADO VIENDO LA TV       0.18      0.31      0.23       184
   SUBIR Y BAJAR ESCALERAS       0.35      0.26      0.29       184
                    TROTAR       0.73      0.50      0.60       161

                  accuracy                           0.28      2737
                 macro avg       0.28      0.28      0.27      2737
              weighted avg       0.28      0.28      0.27      2737


Accuracy capturado en la ejecución 7: 27.66 [%]
F1-score capturado en la ejecución 7: 26.8 [%]

=== EJECUCIÓN 8 ===

--- TRAIN (ejecución 8) ---

--- TEST (ejecución 8) ---
2025-11-07 13:05:45.209199: 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`.
2025-11-07 13:05:45.220928: 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 00:00:1762517145.234847 2772541 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517145.239238 2772541 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517145.249566 2772541 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517145.249593 2772541 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517145.249595 2772541 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517145.249597 2772541 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:05:45.252556: 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 00:00:1762517147.504588 2772541 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13758 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517150.524919 2772670 service.cc:152] XLA service 0x7e128801b690 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517150.524976 2772670 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:05:50.589935: 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 00:00:1762517151.008788 2772670 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517153.539710 2772670 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42:58[0m 5s/step - accuracy: 0.0000e+00 - loss: 4.0287
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0715 - loss: 3.3069        
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0687 - loss: 3.3083
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0688 - loss: 3.3053
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0705 - loss: 3.2997
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0718 - loss: 3.2961
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0737 - loss: 3.2891
[1m 201/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0755 - loss: 3.2792
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0770 - loss: 3.2701
[1m 254/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0785 - loss: 3.2613
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0800 - loss: 3.2527
[1m 310/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0814 - loss: 3.2441
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0826 - loss: 3.2362
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0840 - loss: 3.2275
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0855 - loss: 3.2191
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0871 - loss: 3.2101
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0884 - loss: 3.2027
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0897 - loss: 3.1949
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0910 - loss: 3.1880
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0922 - loss: 3.1812
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0934 - loss: 3.1746
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0945 - loss: 3.1684
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0955 - loss: 3.1623
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0966 - loss: 3.1562
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0976 - loss: 3.1503
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0985 - loss: 3.1448
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0994 - loss: 3.1397
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1003 - loss: 3.1347
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1011 - loss: 3.1297
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1019 - loss: 3.1251
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1027 - loss: 3.1200
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1035 - loss: 3.1151
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1043 - loss: 3.1102
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1051 - loss: 3.1055
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1058 - loss: 3.1009
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1065 - loss: 3.0966
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1072 - loss: 3.0925
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1078 - loss: 3.0886
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1084 - loss: 3.0849
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1090 - loss: 3.0809
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1097 - loss: 3.0768
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1103 - loss: 3.0728
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1109 - loss: 3.0694
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1110 - loss: 3.0689
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1110 - loss: 3.0687 - val_accuracy: 0.2426 - val_loss: 2.3552
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.3750 - loss: 2.5523
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1703 - loss: 2.6856  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1686 - loss: 2.6756
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1722 - loss: 2.6747
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1726 - loss: 2.6756
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1736 - loss: 2.6756
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1740 - loss: 2.6762
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1745 - loss: 2.6763
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1746 - loss: 2.6763
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1747 - loss: 2.6769
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1750 - loss: 2.6771
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1753 - loss: 2.6774
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1756 - loss: 2.6774
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1759 - loss: 2.6771
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1762 - loss: 2.6767
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1765 - loss: 2.6761
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1768 - loss: 2.6752
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.6742
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1773 - loss: 2.6732
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1776 - loss: 2.6722
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.6712
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6702
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1782 - loss: 2.6691
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1783 - loss: 2.6682
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1785 - loss: 2.6673
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1786 - loss: 2.6664
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1787 - loss: 2.6654
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1789 - loss: 2.6645
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1790 - loss: 2.6637
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1791 - loss: 2.6628
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.6621
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.6613
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.6604
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6596
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.6588
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6580
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.6571
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1799 - loss: 2.6563
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1800 - loss: 2.6553
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1801 - loss: 2.6544
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.6535
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1803 - loss: 2.6526
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6517
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6510 - val_accuracy: 0.2507 - val_loss: 2.2490
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.5083
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2369 - loss: 2.4953  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2326 - loss: 2.5069
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2237 - loss: 2.5212
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2203 - loss: 2.5211
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2177 - loss: 2.5224
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2159 - loss: 2.5236
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2153 - loss: 2.5222
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2149 - loss: 2.5206
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2149 - loss: 2.5184
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2149 - loss: 2.5164
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.5146
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2145 - loss: 2.5139
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2143 - loss: 2.5138
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2141 - loss: 2.5135
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2139 - loss: 2.5132
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2137 - loss: 2.5128
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2134 - loss: 2.5124
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2132 - loss: 2.5121
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2129 - loss: 2.5120
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2126 - loss: 2.5118
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2123 - loss: 2.5116
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2121 - loss: 2.5114
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2118 - loss: 2.5113
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2116 - loss: 2.5111
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2114 - loss: 2.5108
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.5105
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.5101
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2108 - loss: 2.5097
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2107 - loss: 2.5090
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2106 - loss: 2.5085
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2106 - loss: 2.5079
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2105 - loss: 2.5074
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2104 - loss: 2.5068
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2104 - loss: 2.5062
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2103 - loss: 2.5056
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2103 - loss: 2.5050
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2102 - loss: 2.5044
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2102 - loss: 2.5039
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2101 - loss: 2.5034
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2101 - loss: 2.5029
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2101 - loss: 2.5024
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2100 - loss: 2.5019
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2100 - loss: 2.5015 - val_accuracy: 0.2756 - val_loss: 2.2070
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.4958
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2274 - loss: 2.4193  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4313
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4330
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2179 - loss: 2.4315
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2175 - loss: 2.4314
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4305
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4285
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4287
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4292
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4295
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4295
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4290
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4284
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4278
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4276
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4276
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4275
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4273
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4272
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4270
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4269
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4266
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4262
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4257
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4253
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4249
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4244
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4239
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4234
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4229
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4225
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4221
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4217
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4213
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4210
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4207
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4204
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4202
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4200
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4197
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4195
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4192
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4191 - val_accuracy: 0.2914 - val_loss: 2.1856
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.8050
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2072 - loss: 2.4571  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2269 - loss: 2.3900
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2298 - loss: 2.3776
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3761
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3739
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3724
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3721
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3717
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3703
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2278 - loss: 2.3688
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3676
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3667
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3662
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3659
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3656
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3654
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3653
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3651
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2281 - loss: 2.3649
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2281 - loss: 2.3648
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2282 - loss: 2.3648
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2283 - loss: 2.3649
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2284 - loss: 2.3648
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2284 - loss: 2.3649
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2285 - loss: 2.3648
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3649
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3650
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3650
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3650
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3649
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3648
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3648
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3648
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3647
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3646
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3645
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3643
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3641
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3639
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3637
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3634
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3631
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3630 - val_accuracy: 0.3113 - val_loss: 2.1524
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0882
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3135  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2195 - loss: 2.3513
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2236 - loss: 2.3469
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2271 - loss: 2.3403
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2308 - loss: 2.3344
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3333
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2335 - loss: 2.3328
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2345 - loss: 2.3317
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3312
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2351 - loss: 2.3315
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2350 - loss: 2.3324
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3329
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3331
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3335
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2350 - loss: 2.3337
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2353 - loss: 2.3333
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2357 - loss: 2.3325
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2361 - loss: 2.3318
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.3313
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2368 - loss: 2.3307
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.3300
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2376 - loss: 2.3294
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3288
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2382 - loss: 2.3283
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2384 - loss: 2.3279
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2386 - loss: 2.3275
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2388 - loss: 2.3270
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2390 - loss: 2.3265
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2391 - loss: 2.3259
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2393 - loss: 2.3254
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2394 - loss: 2.3249
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2396 - loss: 2.3245
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2397 - loss: 2.3243
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2398 - loss: 2.3240
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2400 - loss: 2.3236
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2401 - loss: 2.3232
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2402 - loss: 2.3229
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2403 - loss: 2.3225
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2404 - loss: 2.3222
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2405 - loss: 2.3220
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2407 - loss: 2.3217
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2407 - loss: 2.3215 - val_accuracy: 0.3115 - val_loss: 2.1409
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.5190
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2559 - loss: 2.3036  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2576 - loss: 2.3043
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2535 - loss: 2.3078
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2500 - loss: 2.3100
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2475 - loss: 2.3108
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2465 - loss: 2.3081
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2455 - loss: 2.3062
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2444 - loss: 2.3045
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2436 - loss: 2.3039
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3028
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3019
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2422 - loss: 2.3010
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3004
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2417 - loss: 2.3001
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2416 - loss: 2.3000
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2415 - loss: 2.2997
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2415 - loss: 2.2992
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2416 - loss: 2.2985
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2417 - loss: 2.2980
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2418 - loss: 2.2975
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.2969
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2421 - loss: 2.2962
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2422 - loss: 2.2956
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2424 - loss: 2.2951
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.2945
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2938
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2932
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2429 - loss: 2.2927
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.2921
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2915
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.2910
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2437 - loss: 2.2905
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2439 - loss: 2.2900
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2442 - loss: 2.2895
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2444 - loss: 2.2890
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2447 - loss: 2.2885
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2449 - loss: 2.2880
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2452 - loss: 2.2876
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2454 - loss: 2.2871
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2456 - loss: 2.2867
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2458 - loss: 2.2863
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2461 - loss: 2.2858 - val_accuracy: 0.3155 - val_loss: 2.1260
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1017
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2664 - loss: 2.2028  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2680 - loss: 2.2150
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2692 - loss: 2.2140
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2684 - loss: 2.2198
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2677 - loss: 2.2239
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2674 - loss: 2.2269
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2669 - loss: 2.2290
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.2289
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.2280
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2678 - loss: 2.2274
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.2270
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2678 - loss: 2.2274
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.2280
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.2282
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.2283
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2667 - loss: 2.2286
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2664 - loss: 2.2287
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2661 - loss: 2.2288
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2657 - loss: 2.2290
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 2.2292
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2651 - loss: 2.2296
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2647 - loss: 2.2300
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2644 - loss: 2.2303
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2308
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2638 - loss: 2.2311
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2313
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.2315
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2317
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2319
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2321
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2323
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2626 - loss: 2.2325
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2625 - loss: 2.2327
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2624 - loss: 2.2330
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2622 - loss: 2.2333
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2620 - loss: 2.2335
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2337
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2338
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2339
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2340
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2340
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2340 - val_accuracy: 0.3083 - val_loss: 2.1330
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.6456
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2926  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2636 - loss: 2.2499
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2642 - loss: 2.2445
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2644 - loss: 2.2419
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2648 - loss: 2.2392
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2649 - loss: 2.2381
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2649 - loss: 2.2362
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2649 - loss: 2.2340
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2652 - loss: 2.2318
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.2303
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2294
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2662 - loss: 2.2290
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2663 - loss: 2.2285
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2663 - loss: 2.2281
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2664 - loss: 2.2277
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2667 - loss: 2.2271
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.2263
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.2255
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.2247
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2677 - loss: 2.2239
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.2233
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2680 - loss: 2.2226
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.2219
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.2212
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2686 - loss: 2.2207
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2201
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2690 - loss: 2.2197
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2691 - loss: 2.2192
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2692 - loss: 2.2188
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2183
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.2180
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.2177
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2696 - loss: 2.2174
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.2171
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.2168
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.2165
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.2162
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.2159
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.2157
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.2155
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.2152
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2702 - loss: 2.2150 - val_accuracy: 0.3317 - val_loss: 2.1232
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.0862
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2456 - loss: 2.2260  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2198
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2651 - loss: 2.2096
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1975
[1m 124/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2736 - loss: 2.1914
[1m 151/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2751 - loss: 2.1875
[1m 177/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1857
[1m 206/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1837
[1m 231/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2781 - loss: 2.1829
[1m 259/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2782 - loss: 2.1827
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1820
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2786 - loss: 2.1812
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1811
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1818
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2782 - loss: 2.1826
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 2.1835
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1848
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1859
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1868
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1874
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1876
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1878
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1879
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1879
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1879
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1879
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1880
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1880
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1879
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1879
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1878
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1877
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1875
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1874
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1872
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1871
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1870
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1869
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1868
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1867
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1866
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1865
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1865 - val_accuracy: 0.3180 - val_loss: 2.1161
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0952
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1663  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1675
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1638
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1557
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1492
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1440
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1404
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1386
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1371
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1361
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1354
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1353
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1356
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1362
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1370
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1376
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1380
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1386
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1391
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1398
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1406
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1412
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1417
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1423
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1427
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1432
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1438
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1445
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1452
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1459
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1467
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1475
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1482
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1487
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1492
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1497
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1502
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1507
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1510
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1515
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1519
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1523
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1525 - val_accuracy: 0.3298 - val_loss: 2.1022
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2500 - loss: 2.4178
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2379 - loss: 2.2560  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2156
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2691 - loss: 2.1952
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1815
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1757
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1719
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1683
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1649
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1633
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1618
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1609
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1608
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1608
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1605
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1603
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1601
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1600
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1601
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1602
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1603
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1604
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1605
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1607
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1608
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1609
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1608
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1608
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1607
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1606
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1605
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1603
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1602
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1600
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1597
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1595
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1592
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1590
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1588
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1585
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1582
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1579
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1576
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1574 - val_accuracy: 0.3391 - val_loss: 2.0927
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.5738
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2790 - loss: 2.0872  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2759 - loss: 2.1319
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2782 - loss: 2.1370
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1391
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1401
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1433
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1458
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1477
[1m 255/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1491
[1m 283/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1497
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1499
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1501
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1504
[1m 393/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1503
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1501
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1499
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1495
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1489
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1484
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1477
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1472
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1466
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2874 - loss: 2.1457
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1452
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2880 - loss: 2.1447
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1441
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1437
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1431
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1426
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1422
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2895 - loss: 2.1417
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2898 - loss: 2.1413
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2900 - loss: 2.1409
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2902 - loss: 2.1406
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2903 - loss: 2.1403
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2905 - loss: 2.1400
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2906 - loss: 2.1397
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2908 - loss: 2.1394
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2909 - loss: 2.1392
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 2.1390
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2911 - loss: 2.1388
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2912 - loss: 2.1386 - val_accuracy: 0.3311 - val_loss: 2.0959
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.9040
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2991 - loss: 2.0664  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2894 - loss: 2.0835
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2886 - loss: 2.0893
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 2.0929
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.0936
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2913 - loss: 2.0914
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2930 - loss: 2.0891
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 2.0874
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 2.0870
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.0874
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.0885
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0899
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0911
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0921
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 2.0927
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0931
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 2.0934
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2966 - loss: 2.0938
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 2.0942
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 2.0945
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 2.0947
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 2.0951
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2974 - loss: 2.0954
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2976 - loss: 2.0957
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2976 - loss: 2.0960
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 2.0963
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 2.0966
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2978 - loss: 2.0970
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2978 - loss: 2.0974
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2978 - loss: 2.0978
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.0981
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.0985
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.0989
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.0992
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.0994
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.0997
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1001
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1004
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1007
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1009
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1011
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1013
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1013 - val_accuracy: 0.3339 - val_loss: 2.1083
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.4375 - loss: 2.3070
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 2.1235  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2971 - loss: 2.1389
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1332
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1301
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1278
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1253
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1212
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1178
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1152
[1m 283/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1130
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1111
[1m 337/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1096
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1081
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1064
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1051
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1040
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1033
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1029
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1023
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 2.1020
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1017
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3014 - loss: 2.1015
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1011
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 2.1006
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 2.1001
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0997
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0993
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0989
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0986
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0983
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0980
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0977
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0973
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0971
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0968
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0967
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0965
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0963
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0961
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0959
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0957
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0956 - val_accuracy: 0.3129 - val_loss: 2.1028
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.5000 - loss: 1.7004
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0766  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2986 - loss: 2.0869
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2991 - loss: 2.0775
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3018 - loss: 2.0693
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0669
[1m 153/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0658
[1m 179/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 2.0648
[1m 206/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0637
[1m 232/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0627
[1m 260/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0623
[1m 284/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0621
[1m 310/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0619
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0616
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0616
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0616
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0615
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0613
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0611
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0611
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0613
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0614
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0614
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0615
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0615
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0617
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0619
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0622
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0624
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0626
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0627
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3100 - loss: 2.0628
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0629
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0630
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0631
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0632
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0633
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0634
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0635
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0635
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0636
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0636
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0637
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0638 - val_accuracy: 0.3254 - val_loss: 2.1052
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8779
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3395 - loss: 1.9522  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3362 - loss: 1.9873
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3331 - loss: 2.0006
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3302 - loss: 2.0125
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3283 - loss: 2.0194
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0246
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0281
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0305
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0328
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0350
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0364
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0374
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0382
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0386
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0390
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0394
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0399
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0404
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0411
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3255 - loss: 2.0416
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0421
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0427
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0433
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0439
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0445
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0450
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0455
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0460
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0465
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0470
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0474
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0479
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0483
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0488
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0492
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0495
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0498
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0501
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0503
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0505
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0508
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0509
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0510 - val_accuracy: 0.3363 - val_loss: 2.1149

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 633ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 964us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:11[0m 852ms/step
[1m 52/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 993us/step  
[1m105/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 970us/step
[1m161/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 947us/step
[1m211/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 961us/step
[1m263/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 965us/step
[1m313/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 971us/step
[1m365/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 971us/step
[1m416/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 973us/step
[1m469/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 970us/step
[1m521/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 971us/step
[1m577/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 964us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 952us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 48/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m102/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 997us/step
[1m154/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 986us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 35.58 [%]
Global F1 score (validation) = 34.16 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.02622577 0.02617247 0.02777828 ... 0.01848645 0.12067302 0.00721188]
 [0.00159505 0.00166834 0.00264858 ... 0.11459147 0.00983562 0.00330896]
 [0.00039699 0.00222392 0.00105072 ... 0.00471648 0.00098721 0.00068444]
 ...
 [0.09989168 0.08020829 0.15872246 ... 0.01289622 0.21405521 0.09480316]
 [0.15917926 0.08210351 0.10249258 ... 0.02978165 0.12147845 0.06612659]
 [0.09512597 0.06106948 0.16195397 ... 0.00671019 0.1186765  0.12556888]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 40.79 [%]
Global accuracy score (test) = 29.12 [%]
Global F1 score (train) = 39.9 [%]
Global F1 score (test) = 27.58 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.30      0.43      0.35       184
 CAMINAR CON MÓVIL O LIBRO       0.22      0.18      0.20       184
       CAMINAR USUAL SPEED       0.19      0.10      0.13       184
            CAMINAR ZIGZAG       0.25      0.27      0.26       184
          DE PIE BARRIENDO       0.42      0.23      0.30       184
   DE PIE DOBLANDO TOALLAS       0.30      0.40      0.34       184
    DE PIE MOVIENDO LIBROS       0.26      0.15      0.19       184
          DE PIE USANDO PC       0.13      0.09      0.11       184
        FASE REPOSO CON K5       0.32      0.74      0.45       184
INCREMENTAL CICLOERGOMETRO       0.46      0.40      0.42       184
           SENTADO LEYENDO       0.29      0.28      0.28       184
         SENTADO USANDO PC       0.05      0.03      0.04       184
      SENTADO VIENDO LA TV       0.19      0.22      0.20       184
   SUBIR Y BAJAR ESCALERAS       0.30      0.40      0.35       184
                    TROTAR       0.57      0.48      0.52       161

                  accuracy                           0.29      2737
                 macro avg       0.28      0.29      0.28      2737
              weighted avg       0.28      0.29      0.27      2737


Accuracy capturado en la ejecución 8: 29.12 [%]
F1-score capturado en la ejecución 8: 27.58 [%]

=== EJECUCIÓN 9 ===

--- TRAIN (ejecución 9) ---

--- TEST (ejecución 9) ---
2025-11-07 13:06:53.802872: 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`.
2025-11-07 13:06:53.814298: 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 00:00:1762517213.827928 2775499 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517213.832234 2775499 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517213.842241 2775499 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517213.842261 2775499 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517213.842263 2775499 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517213.842264 2775499 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:06:53.845506: 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 00:00:1762517216.085063 2775499 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13758 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517219.149293 2775603 service.cc:152] XLA service 0x76a31001ba20 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517219.149353 2775603 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:06:59.220507: 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 00:00:1762517219.641272 2775603 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517222.155830 2775603 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43:38[0m 5s/step - accuracy: 0.1250 - loss: 3.0263
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0863 - loss: 3.2867    
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0848 - loss: 3.2778
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0850 - loss: 3.2618
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0863 - loss: 3.2528
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0872 - loss: 3.2439
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0874 - loss: 3.2345
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0879 - loss: 3.2264
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0885 - loss: 3.2173
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0893 - loss: 3.2070
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0901 - loss: 3.1978
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0910 - loss: 3.1893
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0921 - loss: 3.1815
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0935 - loss: 3.1727
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0948 - loss: 3.1645
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0961 - loss: 3.1567
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0973 - loss: 3.1489
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0983 - loss: 3.1424
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0993 - loss: 3.1359
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1002 - loss: 3.1294
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1012 - loss: 3.1232
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1022 - loss: 3.1171
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1031 - loss: 3.1116
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1041 - loss: 3.1059
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1051 - loss: 3.1001
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1059 - loss: 3.0952
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1067 - loss: 3.0900
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1075 - loss: 3.0851
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1082 - loss: 3.0808
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1089 - loss: 3.0768
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1097 - loss: 3.0719
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1103 - loss: 3.0678
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1111 - loss: 3.0634
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1119 - loss: 3.0589
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1125 - loss: 3.0547
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1132 - loss: 3.0508
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1139 - loss: 3.0466
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1146 - loss: 3.0426
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1153 - loss: 3.0387
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1161 - loss: 3.0346
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1167 - loss: 3.0312
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1173 - loss: 3.0274
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1175 - loss: 3.0261
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1176 - loss: 3.0260 - val_accuracy: 0.2458 - val_loss: 2.3356
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.0110
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1960 - loss: 2.5395  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1936 - loss: 2.5809
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1934 - loss: 2.5992
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1909 - loss: 2.6136
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1892 - loss: 2.6205
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1879 - loss: 2.6236
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1868 - loss: 2.6258
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1861 - loss: 2.6269
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1852 - loss: 2.6289
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.6303
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1838 - loss: 2.6306
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1833 - loss: 2.6305
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1828 - loss: 2.6302
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6295
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1825 - loss: 2.6290
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1825 - loss: 2.6284
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6276
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6268
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1828 - loss: 2.6259
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.6248
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1831 - loss: 2.6239
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1831 - loss: 2.6229
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.6219
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.6212
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.6205
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1833 - loss: 2.6198
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.6192
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1834 - loss: 2.6185
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.6178
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1835 - loss: 2.6171
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1836 - loss: 2.6163
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1837 - loss: 2.6155
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1838 - loss: 2.6148
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1839 - loss: 2.6142
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1839 - loss: 2.6135
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1840 - loss: 2.6128
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1841 - loss: 2.6121
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1843 - loss: 2.6113
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1844 - loss: 2.6105
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1845 - loss: 2.6098
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.6091
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1847 - loss: 2.6087 - val_accuracy: 0.2762 - val_loss: 2.2644
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2917
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2593 - loss: 2.3927  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2465 - loss: 2.4218
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2378 - loss: 2.4385
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2343 - loss: 2.4440
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2309 - loss: 2.4484
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2285 - loss: 2.4503
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2261 - loss: 2.4537
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2243 - loss: 2.4570
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2228 - loss: 2.4591
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2215 - loss: 2.4613
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2205 - loss: 2.4636
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2197 - loss: 2.4654
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2190 - loss: 2.4670
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4682
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4695
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2174 - loss: 2.4703
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2170 - loss: 2.4711
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2167 - loss: 2.4718
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4724
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4730
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2160 - loss: 2.4734
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2158 - loss: 2.4736
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2156 - loss: 2.4737
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2156 - loss: 2.4737
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2155 - loss: 2.4736
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2155 - loss: 2.4734
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2154 - loss: 2.4732
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2153 - loss: 2.4730
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2153 - loss: 2.4727
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2152 - loss: 2.4724
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2152 - loss: 2.4721
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2151 - loss: 2.4718
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2151 - loss: 2.4714
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2151 - loss: 2.4710
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2150 - loss: 2.4706
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2149 - loss: 2.4703
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2148 - loss: 2.4699
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2148 - loss: 2.4696
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2147 - loss: 2.4692
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2147 - loss: 2.4689
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2146 - loss: 2.4686
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2146 - loss: 2.4683
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2146 - loss: 2.4681 - val_accuracy: 0.2916 - val_loss: 2.2032
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3750 - loss: 2.3390
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2562 - loss: 2.3829  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2354 - loss: 2.3945
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3914
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2316 - loss: 2.3902
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2302 - loss: 2.3919
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3924
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2273 - loss: 2.3933
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2256 - loss: 2.3949
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2241 - loss: 2.3967
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2229 - loss: 2.3979
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2218 - loss: 2.3990
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2210 - loss: 2.3997
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2205 - loss: 2.4000
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2202 - loss: 2.4003
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2199 - loss: 2.4004
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2197 - loss: 2.4003
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2195 - loss: 2.4002
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2193 - loss: 2.4003
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2191 - loss: 2.4004
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4005
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4006
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4006
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4005
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4004
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4003
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4003
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4002
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4000
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2188 - loss: 2.3999
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.3997
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.3995
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2190 - loss: 2.3993
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2191 - loss: 2.3991
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2192 - loss: 2.3990
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2192 - loss: 2.3987
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2193 - loss: 2.3985
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.3982
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2195 - loss: 2.3979
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2196 - loss: 2.3977
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2196 - loss: 2.3974
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2197 - loss: 2.3971
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2198 - loss: 2.3968
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2198 - loss: 2.3968 - val_accuracy: 0.2944 - val_loss: 2.1980
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.5577
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2517 - loss: 2.3744  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2487 - loss: 2.3635
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2457 - loss: 2.3585
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2438 - loss: 2.3586
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2422 - loss: 2.3585
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2415 - loss: 2.3569
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2410 - loss: 2.3560
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2406 - loss: 2.3551
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2404 - loss: 2.3542
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2399 - loss: 2.3538
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2392 - loss: 2.3537
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2385 - loss: 2.3542
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2380 - loss: 2.3548
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2375 - loss: 2.3557
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2371 - loss: 2.3566
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2366 - loss: 2.3577
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2363 - loss: 2.3585
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.3592
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2357 - loss: 2.3598
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2354 - loss: 2.3602
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2352 - loss: 2.3607
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2350 - loss: 2.3610
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3613
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3616
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3617
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3618
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3618
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3617
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.3616
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.3615
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3615
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3613
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3611
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3609
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.3607
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.3604
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3601
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3599
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3595
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3592
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3588
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3584
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3583 - val_accuracy: 0.3123 - val_loss: 2.1483
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.0309
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2757 - loss: 2.2265  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2638
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2759
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.2825
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2850
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2459 - loss: 2.2869
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2452 - loss: 2.2883
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2447 - loss: 2.2892
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2443 - loss: 2.2902
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2440 - loss: 2.2913
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2435 - loss: 2.2924
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2930
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2430 - loss: 2.2934
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2941
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2426 - loss: 2.2947
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2424 - loss: 2.2951
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2424 - loss: 2.2953
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2423 - loss: 2.2955
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2422 - loss: 2.2957
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2420 - loss: 2.2959
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2420 - loss: 2.2961
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2418 - loss: 2.2963
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2417 - loss: 2.2966
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2416 - loss: 2.2969
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2415 - loss: 2.2971
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.2973
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2413 - loss: 2.2974
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2412 - loss: 2.2975
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2412 - loss: 2.2974
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.2972
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.2971
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.2970
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.2969
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2410 - loss: 2.2968
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.2966
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.2964
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2411 - loss: 2.2962
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2412 - loss: 2.2960
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2412 - loss: 2.2958
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2413 - loss: 2.2955
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.2953
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2415 - loss: 2.2952 - val_accuracy: 0.3091 - val_loss: 2.1625
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0591
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2760 - loss: 2.2423  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2655 - loss: 2.2602
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2665
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2711
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2730
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2567 - loss: 2.2754
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2768
[1m 205/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2773
[1m 234/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2783
[1m 260/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2784
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2782
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2780
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2779
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2780
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2780
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2780
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2779
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2777
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2775
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2772
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2768
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2763
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2756
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2750
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2744
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2739
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2735
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2732
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2728
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2724
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2720
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2717
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2714
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2712
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2708
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2704
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2699
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2695
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2691
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2686
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2683
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2678
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2673 - val_accuracy: 0.3361 - val_loss: 2.1247
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.9035
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2595 - loss: 2.1621  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2729 - loss: 2.1688
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1789
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1867
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1932
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1983
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.2013
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.2031
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.2057
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2792 - loss: 2.2080
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 2.2097
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2787 - loss: 2.2109
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2784 - loss: 2.2119
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 2.2127
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2777 - loss: 2.2133
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2774 - loss: 2.2137
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2771 - loss: 2.2139
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.2140
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.2140
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2760 - loss: 2.2141
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 2.2143
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2753 - loss: 2.2144
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2749 - loss: 2.2145
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2746 - loss: 2.2145
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2744 - loss: 2.2145
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.2145
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2739 - loss: 2.2144
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2736 - loss: 2.2144
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2734 - loss: 2.2143
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2732 - loss: 2.2143
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.2143
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2728 - loss: 2.2142
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.2141
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.2140
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2724 - loss: 2.2139
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.2139
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2721 - loss: 2.2137
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.2136
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2135
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.2134
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.2132
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2716 - loss: 2.2131
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2716 - loss: 2.2130 - val_accuracy: 0.3361 - val_loss: 2.1130
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7052
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0494  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3036 - loss: 2.1133
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1387
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2901 - loss: 2.1517
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1576
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2872 - loss: 2.1621
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1664
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1689
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1706
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1715
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1726
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1742
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1754
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1761
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1766
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1769
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1768
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1766
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1767
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1770
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1774
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1779
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1784
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1787
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1791
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1795
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1799
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1801
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1802
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1802
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1803
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1803
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1802
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1801
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1801
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1800
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2786 - loss: 2.1800
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1799
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1800
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2782 - loss: 2.1800
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2781 - loss: 2.1800
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2780 - loss: 2.1800
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2780 - loss: 2.1800 - val_accuracy: 0.3345 - val_loss: 2.1253
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.8276
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3704 - loss: 2.1558  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3369 - loss: 2.1865
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 2.1899
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3159 - loss: 2.1895
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 2.1875
[1m 172/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.1860
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.1853
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1843
[1m 255/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 2.1838
[1m 285/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2955 - loss: 2.1829
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1818
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1805
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1793
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2912 - loss: 2.1782
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2906 - loss: 2.1773
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2900 - loss: 2.1764
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2895 - loss: 2.1755
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1748
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1743
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2881 - loss: 2.1740
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1736
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1733
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1730
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1724
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1718
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1712
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1708
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1703
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1698
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1694
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1690
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1685
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1682
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1678
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1675
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1671
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1668
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1666
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1664
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1662
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1661
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1659
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1659 - val_accuracy: 0.3208 - val_loss: 2.1345
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.6741
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3427 - loss: 2.0200  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3392 - loss: 2.0344
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3323 - loss: 2.0501
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3288 - loss: 2.0589
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0668
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0752
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0816
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0871
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0911
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0949
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0975
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 2.1000
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3105 - loss: 2.1018
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 2.1035
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.1048
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3086 - loss: 2.1059
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 2.1070
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 2.1081
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 2.1089
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3065 - loss: 2.1096
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 2.1103
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 2.1112
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.1119
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.1128
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 2.1135
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 2.1143
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.1151
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3031 - loss: 2.1158
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.1166
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.1172
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.1179
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3019 - loss: 2.1185
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.1190
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 2.1195
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1199
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1203
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1207
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1210
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1213
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1216
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1218
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1221
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3000 - loss: 2.1223 - val_accuracy: 0.3282 - val_loss: 2.1117
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.8930
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2975 - loss: 2.0676  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2852 - loss: 2.0870
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2855 - loss: 2.0895
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2878 - loss: 2.0897
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2914 - loss: 2.0889
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2944 - loss: 2.0884
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 2.0896
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0910
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 2.0917
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.0925
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0937
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 2.0948
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 2.0960
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2957 - loss: 2.0974
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2957 - loss: 2.0988
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 2.0998
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1007
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1013
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 2.1021
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 2.1028
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 2.1035
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 2.1042
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 2.1047
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 2.1051
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2966 - loss: 2.1053
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1053
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1053
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1052
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2972 - loss: 2.1052
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2973 - loss: 2.1053
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1053
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2975 - loss: 2.1054
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2976 - loss: 2.1054
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 2.1054
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 2.1055
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2978 - loss: 2.1054
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1055
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1055
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1055
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1055
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1055
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1054
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1054 - val_accuracy: 0.3373 - val_loss: 2.1076
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.2500 - loss: 2.4939
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3171 - loss: 2.1492  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3137 - loss: 2.1348
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3132 - loss: 2.1179
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 2.1091
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.1078
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.1074
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.1069
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3091 - loss: 2.1071
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 2.1067
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3075 - loss: 2.1059
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 2.1051
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3066 - loss: 2.1048
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.1043
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 2.1041
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3054 - loss: 2.1040
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.1036
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 2.1032
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 2.1028
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 2.1025
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.1023
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 2.1019
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 2.1014
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3037 - loss: 2.1009
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.1005
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.1001
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3033 - loss: 2.0997
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0994
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0990
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0988
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0986
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0984
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0982
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0981
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0979
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0978
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0977
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0975
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0974
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0972
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0970
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0968
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0966
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0965 - val_accuracy: 0.3383 - val_loss: 2.1071
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3904
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1033  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2986 - loss: 2.0855
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3011 - loss: 2.0760
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0715
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0658
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 2.0619
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0598
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0597
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0603
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0606
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0610
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3067 - loss: 2.0616
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0621
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 2.0627
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0635
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3076 - loss: 2.0641
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0648
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0655
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3078 - loss: 2.0660
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3079 - loss: 2.0664
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0668
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 2.0669
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3082 - loss: 2.0671
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3083 - loss: 2.0672
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3084 - loss: 2.0674
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0676
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3086 - loss: 2.0677
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0677
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3088 - loss: 2.0678
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0678
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0677
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0677
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0676
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0676
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0675
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0674
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0674
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0673
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0673
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0673
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0674
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0674 - val_accuracy: 0.3337 - val_loss: 2.1039
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.4872
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1035  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2969 - loss: 2.0928
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0899
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0861
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 2.0846
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0843
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0832
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0823
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0810
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0799
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0785
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 2.0771
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3088 - loss: 2.0759
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0749
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0740
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0734
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0728
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0724
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0721
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0718
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0715
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0712
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0709
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0708
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0705
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0703
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0701
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0697
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0693
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0688
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0683
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0679
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0675
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0671
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0668
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0664
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0662
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0660
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0658
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3133 - loss: 2.0656
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3133 - loss: 2.0653
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0651
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0650 - val_accuracy: 0.3308 - val_loss: 2.1133
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.6992
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0056  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0078
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0150
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0203
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0256
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0280
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0297
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0312
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0321
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0329
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0329
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0331
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0333
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0339
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0342
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0344
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0345
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0346
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0348
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0351
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0354
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0357
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0360
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0364
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0367
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0370
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0373
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0376
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0379
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0382
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0385
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0388
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0391
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0393
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0394
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0395
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0395
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0396
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0396
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0397
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0396
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0396
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0396 - val_accuracy: 0.3443 - val_loss: 2.0880
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.7809
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0651  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3315 - loss: 2.0341
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3317 - loss: 2.0309
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 2.0316
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0361
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0400
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3215 - loss: 2.0427
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0450
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0455
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0455
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0458
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0460
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0461
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0458
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0451
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0444
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0436
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0429
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0424
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0420
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0415
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0411
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0406
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0401
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0395
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0389
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3215 - loss: 2.0383
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0379
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0375
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0370
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0365
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0360
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0355
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0351
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0348
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0345
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0341
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0338
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0334
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0332
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0329
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0326
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0326 - val_accuracy: 0.3399 - val_loss: 2.0705
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3125 - loss: 1.9518
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3150 - loss: 1.9507  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3203 - loss: 1.9622
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3241 - loss: 1.9711
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3240 - loss: 1.9747
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 1.9754
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 1.9784
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 1.9809
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 1.9827
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3239 - loss: 1.9834
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 1.9833
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 1.9838
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 1.9842
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 1.9844
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 1.9847
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3239 - loss: 1.9852
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3238 - loss: 1.9858
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 1.9866
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 1.9875
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3234 - loss: 1.9882
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3232 - loss: 1.9891
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3231 - loss: 1.9899
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3231 - loss: 1.9904
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 1.9911
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 1.9918
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 1.9927
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3228 - loss: 1.9935
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 1.9943
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 1.9949
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9954
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9959
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 1.9964
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 1.9968
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 1.9972
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 1.9975
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9978
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9981
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9983
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9985
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9987
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9989
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 1.9991
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9993
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9993 - val_accuracy: 0.3385 - val_loss: 2.1307
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.6250 - loss: 1.7477
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3838 - loss: 1.9772  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3705 - loss: 1.9987
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3595 - loss: 2.0084
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3534 - loss: 2.0097
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3498 - loss: 2.0096
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 2.0070
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3459 - loss: 2.0041
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3445 - loss: 2.0025
[1m 254/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 2.0017
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3420 - loss: 2.0011
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3409 - loss: 2.0005
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 2.0002
[1m 366/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.9998
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 1.9993
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3388 - loss: 1.9987
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.9981
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3386 - loss: 1.9975
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.9967
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.9956
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3388 - loss: 1.9944
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3388 - loss: 1.9933
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.9926
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9918
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.9912
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.9906
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 1.9901
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.9896
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.9891
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.9887
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.9884
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.9880
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.9877
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.9874
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.9871
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.9869
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.9868
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.9866
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.9864
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.9863
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.9862
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 1.9861
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3396 - loss: 1.9861 - val_accuracy: 0.3427 - val_loss: 2.1231
Epoch 20/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2018
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3067 - loss: 1.9512  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 1.9536
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 1.9608
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 1.9704
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9722
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 1.9745
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3260 - loss: 1.9765
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3274 - loss: 1.9784
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3283 - loss: 1.9794
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 1.9797
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 1.9805
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 1.9811
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 1.9819
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3297 - loss: 1.9825
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3298 - loss: 1.9829
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3299 - loss: 1.9830
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3300 - loss: 1.9830
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3301 - loss: 1.9832
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3302 - loss: 1.9834
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3304 - loss: 1.9834
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 1.9834
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3308 - loss: 1.9837
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3309 - loss: 1.9840
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 1.9841
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3311 - loss: 1.9842
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3312 - loss: 1.9842
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3313 - loss: 1.9843
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 1.9843
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3316 - loss: 1.9843
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3318 - loss: 1.9842
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3319 - loss: 1.9841
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3321 - loss: 1.9840
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3322 - loss: 1.9838
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3323 - loss: 1.9837
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3324 - loss: 1.9837
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3326 - loss: 1.9836
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3327 - loss: 1.9834
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3328 - loss: 1.9833
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3329 - loss: 1.9832
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3330 - loss: 1.9830
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3331 - loss: 1.9828
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3333 - loss: 1.9826
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3333 - loss: 1.9826 - val_accuracy: 0.3349 - val_loss: 2.1174
Epoch 21/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9571
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3406 - loss: 1.9975  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3535 - loss: 1.9770
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9805
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3456 - loss: 1.9756
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3447 - loss: 1.9710
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3438 - loss: 1.9680
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3440 - loss: 1.9649
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9635
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3448 - loss: 1.9620
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3449 - loss: 1.9607
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3448 - loss: 1.9599
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3447 - loss: 1.9592
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3448 - loss: 1.9583
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3448 - loss: 1.9576
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3449 - loss: 1.9570
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3453 - loss: 1.9562
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3455 - loss: 1.9559
[1m 482/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3456 - loss: 1.9560
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3458 - loss: 1.9563
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3459 - loss: 1.9566
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3460 - loss: 1.9569
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3461 - loss: 1.9570
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3461 - loss: 1.9571
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9571
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9571
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9571
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9571
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3461 - loss: 1.9571
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3461 - loss: 1.9571
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3460 - loss: 1.9571
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3460 - loss: 1.9571
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3461 - loss: 1.9570
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3461 - loss: 1.9568
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9567
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9567
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9568
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3463 - loss: 1.9568
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3464 - loss: 1.9568
[1m1076/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3464 - loss: 1.9568
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3464 - loss: 1.9569
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3464 - loss: 1.9569
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3465 - loss: 1.9569 - val_accuracy: 0.3270 - val_loss: 2.1423
Epoch 22/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.7188
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3438 - loss: 1.9490  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3478 - loss: 1.9356
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3480 - loss: 1.9378
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.9396
[1m 146/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3488 - loss: 1.9378
[1m 176/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3495 - loss: 1.9375
[1m 205/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3503 - loss: 1.9370
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3507 - loss: 1.9369
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3512 - loss: 1.9372
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3513 - loss: 1.9375
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3514 - loss: 1.9376
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3513 - loss: 1.9380
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3513 - loss: 1.9383
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3514 - loss: 1.9386
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3514 - loss: 1.9391
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3513 - loss: 1.9395
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3511 - loss: 1.9400
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3510 - loss: 1.9402
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3510 - loss: 1.9404
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3511 - loss: 1.9404
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3511 - loss: 1.9405
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3511 - loss: 1.9406
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.9407
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.9408
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3514 - loss: 1.9408
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3515 - loss: 1.9407
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3515 - loss: 1.9407
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3516 - loss: 1.9407
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3516 - loss: 1.9407
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3516 - loss: 1.9407
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.9407
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.9406
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.9405
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.9405
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.9404
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.9404
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.9405
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.9406
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.9406
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3517 - loss: 1.9407
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3517 - loss: 1.9408 - val_accuracy: 0.3258 - val_loss: 2.1359

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 646ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 955us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:09[0m 848ms/step
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m103/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 992us/step
[1m158/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 968us/step
[1m213/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 954us/step
[1m270/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 940us/step
[1m319/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 952us/step
[1m367/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 965us/step
[1m424/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 955us/step
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 952us/step
[1m532/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 950us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 47/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m101/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step
[1m157/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 969us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 33.63 [%]
Global F1 score (validation) = 32.27 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[2.24452391e-02 1.57530066e-02 2.94705629e-02 ... 2.51828562e-02
  4.20476981e-02 2.16963533e-02]
 [3.23462021e-03 3.52150085e-03 3.03593907e-03 ... 1.08567879e-01
  1.05198789e-02 3.37090367e-03]
 [4.97252739e-04 2.05290518e-04 2.59664055e-04 ... 1.31817290e-03
  1.07990485e-03 3.72908369e-04]
 ...
 [1.13575101e-01 5.38642704e-02 1.72612861e-01 ... 8.20762012e-03
  1.16771244e-01 1.21579878e-01]
 [1.10491201e-01 5.37979454e-02 2.12427333e-01 ... 9.21662617e-03
  1.06435046e-01 1.34155333e-01]
 [1.98477015e-01 5.02323508e-02 1.19720735e-01 ... 1.03443163e-02
  1.01855479e-01 5.51962070e-02]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 37.96 [%]
Global accuracy score (test) = 27.26 [%]
Global F1 score (train) = 36.9 [%]
Global F1 score (test) = 26.17 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.29      0.29      0.29       184
 CAMINAR CON MÓVIL O LIBRO       0.19      0.17      0.18       184
       CAMINAR USUAL SPEED       0.25      0.27      0.26       184
            CAMINAR ZIGZAG       0.29      0.26      0.27       184
          DE PIE BARRIENDO       0.37      0.21      0.27       184
   DE PIE DOBLANDO TOALLAS       0.33      0.38      0.36       184
    DE PIE MOVIENDO LIBROS       0.27      0.21      0.24       184
          DE PIE USANDO PC       0.11      0.09      0.10       184
        FASE REPOSO CON K5       0.27      0.72      0.40       184
INCREMENTAL CICLOERGOMETRO       0.49      0.40      0.44       184
           SENTADO LEYENDO       0.10      0.08      0.09       184
         SENTADO USANDO PC       0.00      0.00      0.00       184
      SENTADO VIENDO LA TV       0.11      0.14      0.12       184
   SUBIR Y BAJAR ESCALERAS       0.29      0.37      0.32       184
                    TROTAR       0.68      0.53      0.60       161

                  accuracy                           0.27      2737
                 macro avg       0.27      0.27      0.26      2737
              weighted avg       0.27      0.27      0.26      2737


Accuracy capturado en la ejecución 9: 27.26 [%]
F1-score capturado en la ejecución 9: 26.17 [%]

=== EJECUCIÓN 10 ===

--- TRAIN (ejecución 10) ---

--- TEST (ejecución 10) ---
2025-11-07 13:08:15.313819: 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`.
2025-11-07 13:08:15.325140: 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 00:00:1762517295.338643 2779036 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517295.342993 2779036 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517295.353281 2779036 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517295.353304 2779036 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517295.353306 2779036 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517295.353307 2779036 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:08:15.356528: 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 00:00:1762517297.595879 2779036 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13758 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517300.634431 2779140 service.cc:152] XLA service 0x6ffba0001e00 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517300.634503 2779140 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:08:20.707128: 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 00:00:1762517301.126035 2779140 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517303.641967 2779140 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43:05[0m 5s/step - accuracy: 0.0625 - loss: 3.6157
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0432 - loss: 3.4526    
[1m  47/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0522 - loss: 3.3708
[1m  73/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0563 - loss: 3.3462
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0598 - loss: 3.3287
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0643 - loss: 3.3092
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0671 - loss: 3.2973
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0693 - loss: 3.2858
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0710 - loss: 3.2767
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0727 - loss: 3.2666
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0746 - loss: 3.2557
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0763 - loss: 3.2463
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0778 - loss: 3.2368
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0795 - loss: 3.2273
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0811 - loss: 3.2184
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0825 - loss: 3.2105
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0838 - loss: 3.2026
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0850 - loss: 3.1958
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0864 - loss: 3.1883
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0875 - loss: 3.1819
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0888 - loss: 3.1745
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0898 - loss: 3.1686
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0909 - loss: 3.1624
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0920 - loss: 3.1564
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0931 - loss: 3.1503
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0941 - loss: 3.1449
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0951 - loss: 3.1394
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0961 - loss: 3.1340
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0971 - loss: 3.1282
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0980 - loss: 3.1228
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0989 - loss: 3.1178
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0999 - loss: 3.1123
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1009 - loss: 3.1070
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1018 - loss: 3.1016
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1027 - loss: 3.0966
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1035 - loss: 3.0921
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1043 - loss: 3.0873
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1051 - loss: 3.0828
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1058 - loss: 3.0787
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1065 - loss: 3.0750
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1072 - loss: 3.0709
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1080 - loss: 3.0666
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1087 - loss: 3.0627
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1091 - loss: 3.0605
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1091 - loss: 3.0604 - val_accuracy: 0.2569 - val_loss: 2.3742
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.9589
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1812 - loss: 2.7454  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1786 - loss: 2.7315
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1768 - loss: 2.7219
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1763 - loss: 2.7129
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1760 - loss: 2.7057
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1762 - loss: 2.6977
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1773 - loss: 2.6900
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6841
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6805
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6779
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1782 - loss: 2.6758
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1782 - loss: 2.6742
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6731
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6726
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6722
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.6718
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.6714
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.6709
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6702
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6694
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1783 - loss: 2.6685
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1785 - loss: 2.6676
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1787 - loss: 2.6667
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1790 - loss: 2.6654
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.6642
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.6631
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6618
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1799 - loss: 2.6606
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.6596
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6583
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1807 - loss: 2.6572
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1809 - loss: 2.6562
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1811 - loss: 2.6551
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1814 - loss: 2.6539
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1817 - loss: 2.6527
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1819 - loss: 2.6515
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1821 - loss: 2.6505
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6494
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6483
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.6472
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1830 - loss: 2.6460
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.6450
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1833 - loss: 2.6444 - val_accuracy: 0.2672 - val_loss: 2.2969
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1250 - loss: 2.5970
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1352 - loss: 2.6267  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1559 - loss: 2.5941
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1679 - loss: 2.5742
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1742 - loss: 2.5652
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1793 - loss: 2.5582
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.5524
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1855 - loss: 2.5469
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1870 - loss: 2.5434
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1883 - loss: 2.5397
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1896 - loss: 2.5363
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1908 - loss: 2.5326
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1919 - loss: 2.5290
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1926 - loss: 2.5262
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1931 - loss: 2.5241
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1938 - loss: 2.5218
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1943 - loss: 2.5200
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1949 - loss: 2.5182
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1955 - loss: 2.5163
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1961 - loss: 2.5144
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1966 - loss: 2.5128
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1971 - loss: 2.5115
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1974 - loss: 2.5105
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1976 - loss: 2.5097
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1978 - loss: 2.5089
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1981 - loss: 2.5081
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.5073
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1985 - loss: 2.5065
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1988 - loss: 2.5056
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1990 - loss: 2.5048
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1992 - loss: 2.5039
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1995 - loss: 2.5029
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1997 - loss: 2.5020
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1998 - loss: 2.5012
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2000 - loss: 2.5003
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2002 - loss: 2.4996
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2004 - loss: 2.4988
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2005 - loss: 2.4982
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2007 - loss: 2.4975
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2008 - loss: 2.4968
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.4962
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2012 - loss: 2.4955
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2014 - loss: 2.4948
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2014 - loss: 2.4946 - val_accuracy: 0.2771 - val_loss: 2.2219
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0000e+00 - loss: 2.8661
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1920 - loss: 2.4834      
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1975 - loss: 2.4614
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2004 - loss: 2.4546
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2026 - loss: 2.4479
[1m 144/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2042 - loss: 2.4459
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4431
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2068 - loss: 2.4408
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2080 - loss: 2.4384
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2092 - loss: 2.4366
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2100 - loss: 2.4355
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2107 - loss: 2.4344
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2112 - loss: 2.4337
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2117 - loss: 2.4330
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2119 - loss: 2.4325
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2123 - loss: 2.4319
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2127 - loss: 2.4310
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2131 - loss: 2.4301
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2135 - loss: 2.4291
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2140 - loss: 2.4279
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2144 - loss: 2.4267
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.4260
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2150 - loss: 2.4252
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2153 - loss: 2.4244
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2155 - loss: 2.4237
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2157 - loss: 2.4230
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2159 - loss: 2.4224
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2161 - loss: 2.4218
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4211
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4205
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2168 - loss: 2.4200
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2170 - loss: 2.4195
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4191
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2173 - loss: 2.4187
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2174 - loss: 2.4182
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4177
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4173
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4169
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2179 - loss: 2.4166
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4162
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4159
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2181 - loss: 2.4155
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4153 - val_accuracy: 0.3000 - val_loss: 2.2209
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.2338
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2388 - loss: 2.3672  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3747
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2371 - loss: 2.3664
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2384 - loss: 2.3579
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2395 - loss: 2.3524
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2398 - loss: 2.3507
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2401 - loss: 2.3511
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2398 - loss: 2.3517
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2393 - loss: 2.3526
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2388 - loss: 2.3535
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2383 - loss: 2.3547
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3560
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2375 - loss: 2.3571
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2371 - loss: 2.3578
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2367 - loss: 2.3580
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2365 - loss: 2.3580
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2363 - loss: 2.3578
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2361 - loss: 2.3575
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.3572
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2359 - loss: 2.3569
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2357 - loss: 2.3568
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3566
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2354 - loss: 2.3563
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2352 - loss: 2.3561
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2350 - loss: 2.3559
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3556
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2347 - loss: 2.3553
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3552
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3550
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3549
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.3547
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3546
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3545
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3543
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3541
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3539
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2331 - loss: 2.3538
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3535
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3534
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3532
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2328 - loss: 2.3530
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2328 - loss: 2.3527
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2328 - loss: 2.3527 - val_accuracy: 0.3143 - val_loss: 2.1755
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 28ms/step - accuracy: 0.1875 - loss: 2.3371
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2377 - loss: 2.3294  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.3175
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2422 - loss: 2.3141
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2438 - loss: 2.3095
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2453 - loss: 2.3078
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2455 - loss: 2.3078
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2456 - loss: 2.3073
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2453 - loss: 2.3068
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2449 - loss: 2.3063
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2450 - loss: 2.3056
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.3046
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.3043
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2450 - loss: 2.3045
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2449 - loss: 2.3048
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2449 - loss: 2.3047
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2450 - loss: 2.3045
[1m 470/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.3044
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2454 - loss: 2.3040
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2456 - loss: 2.3034
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2458 - loss: 2.3027
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.3021
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2462 - loss: 2.3014
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3008
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2466 - loss: 2.3001
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2995
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2989
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2985
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2981
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2978
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2975
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2973
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2971
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2971
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2970
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2969
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2969
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2968
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2967
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.2967
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.2966
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2966
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2966 - val_accuracy: 0.3143 - val_loss: 2.1476
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3062
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3502  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2387 - loss: 2.3315
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2402 - loss: 2.3199
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3128
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3045
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2442 - loss: 2.2981
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2452 - loss: 2.2935
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.2896
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.2875
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2459 - loss: 2.2863
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2458 - loss: 2.2851
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2456 - loss: 2.2842
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2454 - loss: 2.2836
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2452 - loss: 2.2832
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.2829
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.2825
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.2820
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.2815
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2452 - loss: 2.2811
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2452 - loss: 2.2808
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2453 - loss: 2.2804
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2799
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2457 - loss: 2.2794
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2459 - loss: 2.2789
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.2783
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.2777
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.2770
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2764
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2473 - loss: 2.2759
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2475 - loss: 2.2754
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2477 - loss: 2.2749
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2479 - loss: 2.2745
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2481 - loss: 2.2741
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2483 - loss: 2.2737
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2733
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2729
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2726
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2490 - loss: 2.2723
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2719
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2493 - loss: 2.2716
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2494 - loss: 2.2713
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2710
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2709 - val_accuracy: 0.3198 - val_loss: 2.1352
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9761
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2009 - loss: 2.3029  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2251 - loss: 2.2831
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2365 - loss: 2.2765
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2726
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2720
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2733
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2721
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2706
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2687
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2503 - loss: 2.2664
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2644
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2519 - loss: 2.2636
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2524 - loss: 2.2627
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2528 - loss: 2.2619
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2613
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2608
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2602
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2597
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2592
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2587
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2584
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2581
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2577
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2575
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2573
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2570
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2566
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2562
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2559
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2557
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2553
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2550
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2547
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2544
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2541
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2537
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2534
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2565 - loss: 2.2531
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2566 - loss: 2.2526
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2567 - loss: 2.2523
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2519
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2569 - loss: 2.2515 - val_accuracy: 0.3397 - val_loss: 2.1176
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2191
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2971 - loss: 2.2425  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2912 - loss: 2.2413
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2907 - loss: 2.2306
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2895 - loss: 2.2263
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2877 - loss: 2.2249
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.2231
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2850 - loss: 2.2216
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2836 - loss: 2.2201
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2824 - loss: 2.2186
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.2172
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.2158
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.2145
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2789 - loss: 2.2133
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2784 - loss: 2.2120
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 2.2107
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2776 - loss: 2.2096
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2774 - loss: 2.2084
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.2073
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.2062
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.2053
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 2.2044
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 2.2035
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2768 - loss: 2.2029
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 2.2024
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2766 - loss: 2.2020
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2765 - loss: 2.2016
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2764 - loss: 2.2013
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2762 - loss: 2.2011
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2761 - loss: 2.2010
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2759 - loss: 2.2009
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2758 - loss: 2.2008
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2756 - loss: 2.2007
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2754 - loss: 2.2006
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2753 - loss: 2.2005
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2751 - loss: 2.2005
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2750 - loss: 2.2004
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2749 - loss: 2.2004
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2748 - loss: 2.2004
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2746 - loss: 2.2004
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2745 - loss: 2.2004
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2744 - loss: 2.2004
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2743 - loss: 2.2004
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2743 - loss: 2.2004 - val_accuracy: 0.3345 - val_loss: 2.1206
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8444
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2794 - loss: 2.2107  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2724 - loss: 2.2209
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2722 - loss: 2.2258
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2275
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.2263
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.2237
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2713 - loss: 2.2227
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.2225
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.2211
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2711 - loss: 2.2191
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2713 - loss: 2.2165
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.2140
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2720 - loss: 2.2116
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.2093
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2729 - loss: 2.2077
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2732 - loss: 2.2060
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2736 - loss: 2.2044
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2738 - loss: 2.2031
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2021
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.2012
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2743 - loss: 2.2001
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2745 - loss: 2.1991
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2747 - loss: 2.1980
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2749 - loss: 2.1970
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2751 - loss: 2.1962
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2753 - loss: 2.1955
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2754 - loss: 2.1949
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2755 - loss: 2.1944
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2757 - loss: 2.1938
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2759 - loss: 2.1932
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2761 - loss: 2.1927
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2762 - loss: 2.1922
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1918
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1913
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1908
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1904
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1899
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1895
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1892
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1888
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2775 - loss: 2.1885
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1882
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1881 - val_accuracy: 0.3472 - val_loss: 2.1155
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.4375 - loss: 2.0074
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1523  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1369
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1296
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1270
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2911 - loss: 2.1260
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1270
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1283
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1281
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1282
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1283
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1286
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1293
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1299
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1302
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1305
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1308
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1313
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1319
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1324
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1330
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1337
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1343
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1350
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1356
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1361
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2916 - loss: 2.1367
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1373
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1378
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2911 - loss: 2.1382
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2910 - loss: 2.1386
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2908 - loss: 2.1389
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2907 - loss: 2.1392
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2905 - loss: 2.1395
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2904 - loss: 2.1398
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2903 - loss: 2.1401
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2902 - loss: 2.1403
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2901 - loss: 2.1406
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2900 - loss: 2.1408
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2899 - loss: 2.1410
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2898 - loss: 2.1412
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2898 - loss: 2.1413
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1415
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1416
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1417 - val_accuracy: 0.3427 - val_loss: 2.0850
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0303
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1377  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1457
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1517
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1594
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1622
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1635
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1632
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2904 - loss: 2.1614
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1593
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1570
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1552
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1536
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1520
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 2.1507
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 2.1496
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 2.1488
[1m 476/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1481
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 2.1473
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1464
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1455
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.1447
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1440
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1433
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 2.1427
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1422
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2993 - loss: 2.1418
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1413
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1409
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1406
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1404
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1402
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1400
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1400
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1400
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1400
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1399
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1398
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1397
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1396
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1394
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1393
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1393 - val_accuracy: 0.3647 - val_loss: 2.1102
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2296
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2473 - loss: 2.2105  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2654 - loss: 2.1879
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2723 - loss: 2.1795
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1726
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1663
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1624
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1577
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1534
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1494
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1453
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2909 - loss: 2.1416
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1385
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1361
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1343
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1329
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1318
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1309
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1303
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1295
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1286
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1276
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1269
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1262
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1257
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1251
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1245
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1239
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1234
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1229
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1224
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1219
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2957 - loss: 2.1214
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1210
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 2.1207
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1203
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2962 - loss: 2.1200
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2963 - loss: 2.1197
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 2.1194
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 2.1192
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2966 - loss: 2.1189
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1186
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1185 - val_accuracy: 0.3510 - val_loss: 2.1038
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.9224
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2925 - loss: 2.0639  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2913 - loss: 2.0792
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2953 - loss: 2.0764
[1m 100/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2987 - loss: 2.0751
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0751
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0761
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3033 - loss: 2.0768
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 2.0771
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0779
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 2.0796
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.0805
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0813
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0819
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0824
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0828
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0833
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 2.0836
[1m 482/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0836
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0840
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0845
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0848
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0850
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0853
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0855
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0857
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0859
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0860
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0861
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0862
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0863
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0864
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0865
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0866
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 2.0867
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0868
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0870
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0871
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0872
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0873
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0874
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0875
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0875
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0876
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0877 - val_accuracy: 0.3566 - val_loss: 2.0825
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.4375 - loss: 2.2079
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3622 - loss: 2.0571  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3498 - loss: 2.0338
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3378 - loss: 2.0436
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3309 - loss: 2.0534
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0590
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0627
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0649
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3187 - loss: 2.0658
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0670
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0675
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3163 - loss: 2.0681
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 2.0685
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0690
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0695
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0698
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0696
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0695
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0694
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0695
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0696
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0698
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0700
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0702
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0703
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0704
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0704
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0705
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0705
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0706
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0707
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0708
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0709
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0708
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0708
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0707
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0707
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0706
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0706
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0705
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0703
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0702
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0701
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0701 - val_accuracy: 0.3454 - val_loss: 2.0937
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0030
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3022 - loss: 2.1068  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0742
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0631
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0586
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 2.0551
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0516
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0479
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0450
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0424
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0413
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0412
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0416
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0420
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0429
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0435
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0441
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0449
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0454
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0458
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0462
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0465
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0467
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0468
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0470
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0472
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0474
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0476
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0478
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0480
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0483
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0486
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0489
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0493
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0496
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0499
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0502
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0504
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0507
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0508
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0510
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0511
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0512 - val_accuracy: 0.3421 - val_loss: 2.1001
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2010
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0231  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0261
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0304
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0339
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0365
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0378
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0384
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0378
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0368
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0353
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0349
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0348
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 2.0346
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0343
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0341
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0338
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0337
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0334
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0330
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0327
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0324
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0322
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0321
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0320
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0321
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0322
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0324
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0327
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 2.0330
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0333
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0337
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0340
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0344
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0346
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0349
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0351
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0353
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0356
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 2.0358
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 2.0360
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0362
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0363
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0364 - val_accuracy: 0.3516 - val_loss: 2.1074
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2016
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2820 - loss: 2.0433  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2968 - loss: 2.0373
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.0412
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0419
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0423
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0420
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0417
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 2.0425
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0436
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0441
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0441
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0439
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0436
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0429
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0422
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0417
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0409
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0403
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0397
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0392
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0389
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0385
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0380
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0378
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0375
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0373
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0371
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0369
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0368
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0367
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0366
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0365
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0363
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0362
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0360
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0359
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0357
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0355
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0353
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0351
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0349
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0347 - val_accuracy: 0.3506 - val_loss: 2.0946
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.5047
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3670 - loss: 1.9723  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3667 - loss: 1.9669
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3660 - loss: 1.9636
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3636 - loss: 1.9635
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3608 - loss: 1.9631
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.9632
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3573 - loss: 1.9643
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.9653
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.9655
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3548 - loss: 1.9655
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3542 - loss: 1.9656
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3537 - loss: 1.9658
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3531 - loss: 1.9664
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3525 - loss: 1.9672
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3518 - loss: 1.9684
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3511 - loss: 1.9697
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3505 - loss: 1.9708
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.9718
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3495 - loss: 1.9730
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3489 - loss: 1.9742
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3483 - loss: 1.9756
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3478 - loss: 1.9768
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3474 - loss: 1.9777
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3470 - loss: 1.9788
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3465 - loss: 1.9798
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9807
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3459 - loss: 1.9815
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3456 - loss: 1.9822
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.9828
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3451 - loss: 1.9834
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3449 - loss: 1.9840
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3447 - loss: 1.9846
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9853
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3442 - loss: 1.9859
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3439 - loss: 1.9864
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3437 - loss: 1.9869
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3435 - loss: 1.9874
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9879
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3431 - loss: 1.9884
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.9888
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3428 - loss: 1.9891
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3426 - loss: 1.9895
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3426 - loss: 1.9897 - val_accuracy: 0.3452 - val_loss: 2.0965

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 652ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 945us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:08[0m 847ms/step
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m104/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 974us/step
[1m162/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 938us/step
[1m214/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 944us/step
[1m271/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 930us/step
[1m330/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 915us/step
[1m389/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 906us/step
[1m448/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 900us/step
[1m504/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 900us/step
[1m557/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 906us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 978us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 50/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m103/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 988us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 32.58 [%]
Global F1 score (validation) = 31.75 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[3.3030353e-02 1.4586659e-02 2.5098393e-02 ... 2.3807861e-02
  4.9461488e-02 1.6838040e-02]
 [1.8514291e-03 3.1031633e-03 5.4636379e-03 ... 1.5686408e-01
  6.6794362e-03 6.2192478e-03]
 [4.9951952e-04 8.5694063e-04 2.2253893e-04 ... 5.8352072e-03
  4.1316185e-04 3.9341566e-04]
 ...
 [1.5106919e-01 4.5697473e-02 1.6206247e-01 ... 1.7102793e-03
  1.6798846e-01 1.5546663e-01]
 [1.4549154e-01 1.7292742e-02 4.2965483e-02 ... 4.2512710e-03
  4.7069065e-02 1.2307525e-01]
 [2.3331024e-01 6.7120858e-02 1.2534647e-01 ... 3.4486812e-03
  1.4291671e-01 9.0071619e-02]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 41.99 [%]
Global accuracy score (test) = 26.34 [%]
Global F1 score (train) = 41.77 [%]
Global F1 score (test) = 25.8 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.26      0.57      0.35       184
 CAMINAR CON MÓVIL O LIBRO       0.20      0.19      0.19       184
       CAMINAR USUAL SPEED       0.15      0.09      0.11       184
            CAMINAR ZIGZAG       0.20      0.20      0.20       184
          DE PIE BARRIENDO       0.34      0.23      0.28       184
   DE PIE DOBLANDO TOALLAS       0.26      0.27      0.27       184
    DE PIE MOVIENDO LIBROS       0.24      0.11      0.15       184
          DE PIE USANDO PC       0.11      0.18      0.14       184
        FASE REPOSO CON K5       0.53      0.47      0.50       184
INCREMENTAL CICLOERGOMETRO       0.49      0.46      0.47       184
           SENTADO LEYENDO       0.22      0.12      0.15       184
         SENTADO USANDO PC       0.14      0.09      0.11       184
      SENTADO VIENDO LA TV       0.16      0.26      0.20       184
   SUBIR Y BAJAR ESCALERAS       0.35      0.21      0.26       184
                    TROTAR       0.45      0.54      0.49       161

                  accuracy                           0.26      2737
                 macro avg       0.27      0.27      0.26      2737
              weighted avg       0.27      0.26      0.26      2737


Accuracy capturado en la ejecución 10: 26.34 [%]
F1-score capturado en la ejecución 10: 25.8 [%]

=== EJECUCIÓN 11 ===

--- TRAIN (ejecución 11) ---

--- TEST (ejecución 11) ---
2025-11-07 13:09:29.136286: 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`.
2025-11-07 13:09:29.147742: 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 00:00:1762517369.161095 2782229 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517369.165199 2782229 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517369.175332 2782229 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517369.175353 2782229 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517369.175355 2782229 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517369.175357 2782229 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:09:29.178459: 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 00:00:1762517371.436144 2782229 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517374.439125 2782358 service.cc:152] XLA service 0x7e3fb00040f0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517374.439159 2782358 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:09:34.503173: 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 00:00:1762517374.926612 2782358 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517377.442537 2782358 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42:33[0m 5s/step - accuracy: 0.0625 - loss: 3.3345
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0714 - loss: 3.2770    
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0734 - loss: 3.2709
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0753 - loss: 3.2674
[1m 100/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0788 - loss: 3.2582
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0818 - loss: 3.2476
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0838 - loss: 3.2408
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0851 - loss: 3.2327
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0862 - loss: 3.2257
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0877 - loss: 3.2185
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0893 - loss: 3.2108
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0906 - loss: 3.2041
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0920 - loss: 3.1963
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0932 - loss: 3.1894
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0943 - loss: 3.1829
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0954 - loss: 3.1765
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0965 - loss: 3.1701
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0975 - loss: 3.1639
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0985 - loss: 3.1575
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0995 - loss: 3.1518
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1005 - loss: 3.1455
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1015 - loss: 3.1389
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1025 - loss: 3.1328
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1034 - loss: 3.1270
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1043 - loss: 3.1216
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1052 - loss: 3.1157
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1061 - loss: 3.1105
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1068 - loss: 3.1058
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1077 - loss: 3.1002
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1085 - loss: 3.0949
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1093 - loss: 3.0897
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1100 - loss: 3.0852
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1107 - loss: 3.0803
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1114 - loss: 3.0759
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1120 - loss: 3.0714
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1126 - loss: 3.0671
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1132 - loss: 3.0632
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1138 - loss: 3.0591
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1143 - loss: 3.0551
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1149 - loss: 3.0512
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1155 - loss: 3.0472
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1161 - loss: 3.0432
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1165 - loss: 3.0404
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 5ms/step - accuracy: 0.1165 - loss: 3.0403 - val_accuracy: 0.2505 - val_loss: 2.3547
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m32s[0m 28ms/step - accuracy: 0.1250 - loss: 2.9724
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1833 - loss: 2.6764  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1899 - loss: 2.6653
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1917 - loss: 2.6490
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1907 - loss: 2.6406
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1903 - loss: 2.6363
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1897 - loss: 2.6347
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1888 - loss: 2.6349
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1881 - loss: 2.6350
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1875 - loss: 2.6355
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1869 - loss: 2.6364
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1865 - loss: 2.6371
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1862 - loss: 2.6369
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1861 - loss: 2.6365
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1860 - loss: 2.6361
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1859 - loss: 2.6358
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6357
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.6357
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.6356
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.6354
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1855 - loss: 2.6352
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1854 - loss: 2.6350
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1854 - loss: 2.6347
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6343
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6339
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6334
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6329
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6325
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6320
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6315
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6310
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.6305
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.6300
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.6294
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.6288
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.6281
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1856 - loss: 2.6274
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1857 - loss: 2.6266
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6259
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1858 - loss: 2.6252
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.6246
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.6239
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1860 - loss: 2.6233
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1860 - loss: 2.6232 - val_accuracy: 0.2672 - val_loss: 2.2706
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4856
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2467 - loss: 2.4075  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2329 - loss: 2.4644
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2238 - loss: 2.4863
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4942
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2150 - loss: 2.4998
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2119 - loss: 2.5054
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2099 - loss: 2.5079
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2083 - loss: 2.5095
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2071 - loss: 2.5104
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2061 - loss: 2.5120
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2053 - loss: 2.5137
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2044 - loss: 2.5155
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2036 - loss: 2.5169
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2030 - loss: 2.5178
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2026 - loss: 2.5184
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.5188
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2017 - loss: 2.5190
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2014 - loss: 2.5191
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2012 - loss: 2.5191
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.5191
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2008 - loss: 2.5189
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2007 - loss: 2.5186
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2006 - loss: 2.5184
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2006 - loss: 2.5180
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2006 - loss: 2.5178
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2006 - loss: 2.5175
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2005 - loss: 2.5172
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2005 - loss: 2.5169
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2006 - loss: 2.5166
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2006 - loss: 2.5162
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2007 - loss: 2.5158
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2007 - loss: 2.5154
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2008 - loss: 2.5149
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2009 - loss: 2.5144
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.5138
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.5132
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.5126
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2012 - loss: 2.5121
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2013 - loss: 2.5115
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2014 - loss: 2.5109
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2014 - loss: 2.5103
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2015 - loss: 2.5098
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2015 - loss: 2.5095 - val_accuracy: 0.2764 - val_loss: 2.2286
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.7055
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1878 - loss: 2.3724  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2087 - loss: 2.3657
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2151 - loss: 2.3683
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2170 - loss: 2.3738
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2174 - loss: 2.3783
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.3813
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2177 - loss: 2.3852
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2173 - loss: 2.3903
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2172 - loss: 2.3949
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2171 - loss: 2.3984
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4015
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4036
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4054
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2167 - loss: 2.4070
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4081
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4089
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4094
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4097
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4101
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4102
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4102
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2167 - loss: 2.4102
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2168 - loss: 2.4103
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4105
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4108
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4109
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2170 - loss: 2.4110
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4110
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2172 - loss: 2.4109
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2173 - loss: 2.4109
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2174 - loss: 2.4109
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2175 - loss: 2.4108
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4108
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4108
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4108
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4107
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2179 - loss: 2.4107
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4106
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2181 - loss: 2.4105
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4104
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4103
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4102
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4101 - val_accuracy: 0.3022 - val_loss: 2.1941
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m34s[0m 30ms/step - accuracy: 0.1875 - loss: 2.6341
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2439 - loss: 2.4155  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2378 - loss: 2.4006
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2344 - loss: 2.4013
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2310 - loss: 2.4022
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2294 - loss: 2.4016
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2291 - loss: 2.3992
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3968
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2277 - loss: 2.3962
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2273 - loss: 2.3952
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3942
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.3939
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2263 - loss: 2.3936
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2259 - loss: 2.3936
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2256 - loss: 2.3934
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3929
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3922
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3914
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3905
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3897
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2256 - loss: 2.3888
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2256 - loss: 2.3880
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2256 - loss: 2.3871
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2257 - loss: 2.3863
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2258 - loss: 2.3854
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2258 - loss: 2.3847
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2259 - loss: 2.3840
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2259 - loss: 2.3835
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2259 - loss: 2.3831
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2260 - loss: 2.3827
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2260 - loss: 2.3823
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2260 - loss: 2.3819
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2260 - loss: 2.3815
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2260 - loss: 2.3812
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2260 - loss: 2.3809
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2260 - loss: 2.3806
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2261 - loss: 2.3803
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2261 - loss: 2.3799
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2261 - loss: 2.3796
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2261 - loss: 2.3793
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2261 - loss: 2.3789
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2261 - loss: 2.3786
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2261 - loss: 2.3784 - val_accuracy: 0.3139 - val_loss: 2.1642
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.4714
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2022 - loss: 2.3503  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2104 - loss: 2.3428
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2168 - loss: 2.3313
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2214 - loss: 2.3231
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2241 - loss: 2.3194
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3186
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2264 - loss: 2.3181
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2272 - loss: 2.3171
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3164
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3153
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2294 - loss: 2.3150
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2298 - loss: 2.3150
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2301 - loss: 2.3151
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3150
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2307 - loss: 2.3150
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2310 - loss: 2.3152
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2313 - loss: 2.3152
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3152
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3151
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3150
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3150
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2324 - loss: 2.3151
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3153
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2327 - loss: 2.3155
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2328 - loss: 2.3156
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3159
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3161
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2331 - loss: 2.3162
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3163
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3164
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3164
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.3165
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3165
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3165
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.3165
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.3165
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3166
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3166
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3166
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2345 - loss: 2.3166
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3165
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3164
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3164 - val_accuracy: 0.3157 - val_loss: 2.1525
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0065
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2617 - loss: 2.2653  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2724
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2618
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2556
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2518
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2502
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2526 - loss: 2.2515
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2521 - loss: 2.2530
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2518 - loss: 2.2545
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2562
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2577
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2590
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2503 - loss: 2.2606
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2500 - loss: 2.2621
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2634
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2643
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2648
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2654
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2660
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.2665
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.2672
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2493 - loss: 2.2677
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2684
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2691
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2697
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2483 - loss: 2.2703
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2481 - loss: 2.2709
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2479 - loss: 2.2715
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2477 - loss: 2.2720
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2475 - loss: 2.2724
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2474 - loss: 2.2728
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2473 - loss: 2.2731
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2734
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2737
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2739
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.2741
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2743
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2466 - loss: 2.2744
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.2746
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.2747
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2748
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2749
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2749 - val_accuracy: 0.3234 - val_loss: 2.1297
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.8236
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2210 - loss: 2.3284  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2267 - loss: 2.3089
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3064
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2341 - loss: 2.2968
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.2883
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2414 - loss: 2.2821
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2438 - loss: 2.2779
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2452 - loss: 2.2748
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2727
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2708
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2474 - loss: 2.2696
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.2683
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2482 - loss: 2.2669
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2654
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2646
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2638
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2631
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2494 - loss: 2.2625
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2621
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.2618
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2615
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2612
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2500 - loss: 2.2610
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2502 - loss: 2.2606
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2504 - loss: 2.2603
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.2599
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2506 - loss: 2.2594
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2591
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2587
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2508 - loss: 2.2583
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2508 - loss: 2.2580
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2577
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2574
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2571
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2568
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2566
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2564
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2562
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2508 - loss: 2.2560
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2508 - loss: 2.2558
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2508 - loss: 2.2556
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2554
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2554 - val_accuracy: 0.3268 - val_loss: 2.1312
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4987
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2922  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2643 - loss: 2.2686
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2598
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2514
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.2452
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2708 - loss: 2.2394
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2713 - loss: 2.2359
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2711 - loss: 2.2345
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2335
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.2330
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2687 - loss: 2.2329
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2680 - loss: 2.2325
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2674 - loss: 2.2320
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2669 - loss: 2.2314
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2665 - loss: 2.2309
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2305
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2657 - loss: 2.2300
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 2.2296
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2652 - loss: 2.2292
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2650 - loss: 2.2289
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2648 - loss: 2.2285
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2645 - loss: 2.2284
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2643 - loss: 2.2283
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2283
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2639 - loss: 2.2282
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2280
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2278
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2636 - loss: 2.2275
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2636 - loss: 2.2274
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2272
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2271
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2270
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2268
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2266
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2264
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2262
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2260
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.2259
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2632 - loss: 2.2258
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2257
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2256
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2255
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2254
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2254 - val_accuracy: 0.3371 - val_loss: 2.1238
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.4375 - loss: 1.9165
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3052 - loss: 2.1006  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1215
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1215
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1252
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1286
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1322
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1366
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1410
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2909 - loss: 2.1447
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1485
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1511
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1535
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1552
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1567
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1579
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1592
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1603
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1614
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1626
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1634
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1643
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1651
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1659
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1667
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1675
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1682
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1688
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1696
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1701
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1706
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1712
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2782 - loss: 2.1717
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2780 - loss: 2.1722
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1726
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2777 - loss: 2.1731
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1735
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1739
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1743
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1747
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1751
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1755
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1759
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1762
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1763 - val_accuracy: 0.3363 - val_loss: 2.1261
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0068
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2763 - loss: 2.2372  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2856 - loss: 2.2142
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.2054
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1967
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1917
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1882
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1855
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1834
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1808
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1793
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1781
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1772
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1765
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1762
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1760
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1759
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1758
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1759
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1760
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1761
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1762
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1761
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1760
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1759
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1758
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1757
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1757
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1756
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1756
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1755
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1755
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1754
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1754
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1753
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1752
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1751
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1751
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1750
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2792 - loss: 2.1749
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2792 - loss: 2.1747
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2792 - loss: 2.1746
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1746
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1746 - val_accuracy: 0.3375 - val_loss: 2.1159
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3400
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1902  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2743 - loss: 2.2063
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2736 - loss: 2.1993
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2761 - loss: 2.1883
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2763 - loss: 2.1802
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1735
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2782 - loss: 2.1692
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1662
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1638
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1616
[1m 310/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1599
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1586
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1577
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1571
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1565
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1562
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1559
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1559
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1559
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1559
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1558
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1556
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1553
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1551
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1548
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1545
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1543
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1540
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1537
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1535
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1532
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1531
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1529
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1527
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1525
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1523
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1522
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1521
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1521
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1520
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1520
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1519
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1519 - val_accuracy: 0.3450 - val_loss: 2.0980
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 1.9724
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3037 - loss: 2.1477  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3036 - loss: 2.1391
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3053 - loss: 2.1335
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 2.1314
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3031 - loss: 2.1312
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3025 - loss: 2.1306
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.1311
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1313
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1313
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1316
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.1325
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 2.1338
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2966 - loss: 2.1351
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1359
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2955 - loss: 2.1363
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1365
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1366
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2948 - loss: 2.1368
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1371
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1375
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1378
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2936 - loss: 2.1380
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1381
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1380
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1379
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1378
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1377
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1376
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1374
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1374
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1372
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1370
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1368
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1367
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1365
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1363
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1362
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1361
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1359
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1359
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1358
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1357
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1357 - val_accuracy: 0.3423 - val_loss: 2.0803
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9513
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2567 - loss: 2.1273  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2728 - loss: 2.1140
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2786 - loss: 2.1094
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1087
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1123
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1160
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1183
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1189
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1188
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1185
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1180
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1173
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2869 - loss: 2.1164
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1159
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1154
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1148
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2895 - loss: 2.1142
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2902 - loss: 2.1136
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2908 - loss: 2.1129
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1124
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1118
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1113
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 2.1109
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1106
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1102
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1099
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1098
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1097
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1096
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1095
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1094
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1093
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1092
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2957 - loss: 2.1091
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1090
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 2.1090
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1089
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2963 - loss: 2.1088
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 2.1088
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 2.1087
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 2.1087
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2966 - loss: 2.1087
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2966 - loss: 2.1087 - val_accuracy: 0.3310 - val_loss: 2.0892
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1984
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2944 - loss: 2.2039  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1811
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2903 - loss: 2.1671
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2902 - loss: 2.1576
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1490
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 2.1433
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1384
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1334
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1290
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2955 - loss: 2.1246
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 2.1210
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1182
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1155
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 2.1137
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 2.1118
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2978 - loss: 2.1102
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1092
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1081
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1071
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.1062
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2988 - loss: 2.1052
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1041
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 2.1030
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1019
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1008
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0998
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0991
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.0983
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0976
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0969
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.0964
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.0960
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 2.0957
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0955
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0953
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 2.0950
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 2.0948
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0947
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 2.0944
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0941
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0939
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0936
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 2.0934
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3018 - loss: 2.0934 - val_accuracy: 0.3413 - val_loss: 2.1025
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.9864
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3421 - loss: 2.0137  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3317 - loss: 2.0421
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3279 - loss: 2.0468
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0506
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0529
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0554
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0574
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0587
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0595
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0599
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0609
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0620
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0630
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0635
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0638
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0640
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3188 - loss: 2.0639
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0640
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0641
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0642
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0643
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0643
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0643
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0644
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3166 - loss: 2.0644
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3165 - loss: 2.0645
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3162 - loss: 2.0646
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3160 - loss: 2.0649
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3158 - loss: 2.0650
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 2.0651
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0653
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0654
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0655
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0656
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0658
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0659
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0661
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0663
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0664
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0666
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0667
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0669
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0669 - val_accuracy: 0.3270 - val_loss: 2.0894
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0209
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1201  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2795 - loss: 2.0993
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2810 - loss: 2.0908
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2835 - loss: 2.0868
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.0853
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2869 - loss: 2.0846
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2881 - loss: 2.0828
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.0812
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2904 - loss: 2.0808
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2912 - loss: 2.0804
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2922 - loss: 2.0805
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.0803
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 2.0801
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2952 - loss: 2.0798
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0794
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 2.0789
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 2.0786
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 2.0785
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 2.0784
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2991 - loss: 2.0782
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 2.0781
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0781
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 2.0780
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.0779
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0777
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.0775
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3013 - loss: 2.0773
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0770
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0767
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0764
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0760
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0757
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0753
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0749
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0744
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0740
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0736
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0732
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0729
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0726
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0723
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 2.0720
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0718 - val_accuracy: 0.3306 - val_loss: 2.0855
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0365
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3649 - loss: 2.0428  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3533 - loss: 2.0319
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3472 - loss: 2.0324
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3450 - loss: 2.0298
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3420 - loss: 2.0300
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3391 - loss: 2.0295
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3361 - loss: 2.0296
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3341 - loss: 2.0297
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 2.0302
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3314 - loss: 2.0309
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0313
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3298 - loss: 2.0311
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 2.0308
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 2.0305
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3282 - loss: 2.0304
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0306
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0308
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0310
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0311
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0312
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0312
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0312
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0313
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0314
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0314
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0314
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0314
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0315
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0317
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0319
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0320
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0321
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0324
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 2.0327
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0330
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0332
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0335
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0337
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0338
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0340
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0342
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0343
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0344 - val_accuracy: 0.3443 - val_loss: 2.1022

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m53s[0m 634ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 957us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:16[0m 861ms/step
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m108/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 946us/step
[1m161/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 946us/step
[1m215/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 945us/step
[1m270/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 941us/step
[1m326/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 933us/step
[1m379/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 936us/step
[1m435/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 931us/step
[1m488/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 933us/step
[1m547/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 925us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 931us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 54/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 958us/step
[1m111/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 922us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 34.54 [%]
Global F1 score (validation) = 33.04 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.02044711 0.01878647 0.02549873 ... 0.02470927 0.05261115 0.01530293]
 [0.00381934 0.00408123 0.00181336 ... 0.10800286 0.01026692 0.00377257]
 [0.00096672 0.0013261  0.00090772 ... 0.00437703 0.00174519 0.00181912]
 ...
 [0.1654597  0.04964326 0.17603981 ... 0.00425317 0.19315356 0.13194545]
 [0.15839969 0.0554508  0.19525918 ... 0.00693897 0.14807174 0.11151128]
 [0.1315814  0.06287587 0.1969753  ... 0.01036778 0.12952119 0.08664056]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 40.84 [%]
Global accuracy score (test) = 28.02 [%]
Global F1 score (train) = 39.79 [%]
Global F1 score (test) = 26.76 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.31      0.57      0.40       184
 CAMINAR CON MÓVIL O LIBRO       0.18      0.22      0.20       184
       CAMINAR USUAL SPEED       0.21      0.21      0.21       184
            CAMINAR ZIGZAG       0.30      0.18      0.23       184
          DE PIE BARRIENDO       0.34      0.18      0.24       184
   DE PIE DOBLANDO TOALLAS       0.30      0.24      0.27       184
    DE PIE MOVIENDO LIBROS       0.25      0.20      0.22       184
          DE PIE USANDO PC       0.10      0.11      0.11       184
        FASE REPOSO CON K5       0.33      0.70      0.45       184
INCREMENTAL CICLOERGOMETRO       0.54      0.44      0.48       184
           SENTADO LEYENDO       0.21      0.12      0.15       184
         SENTADO USANDO PC       0.43      0.05      0.09       184
      SENTADO VIENDO LA TV       0.13      0.21      0.16       184
   SUBIR Y BAJAR ESCALERAS       0.30      0.28      0.29       184
                    TROTAR       0.51      0.51      0.51       161

                  accuracy                           0.28      2737
                 macro avg       0.30      0.28      0.27      2737
              weighted avg       0.29      0.28      0.27      2737


Accuracy capturado en la ejecución 11: 28.02 [%]
F1-score capturado en la ejecución 11: 26.76 [%]

=== EJECUCIÓN 12 ===

--- TRAIN (ejecución 12) ---

--- TEST (ejecución 12) ---
2025-11-07 13:10:40.443648: 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`.
2025-11-07 13:10:40.455065: 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 00:00:1762517440.468400 2785299 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517440.472377 2785299 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517440.482544 2785299 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517440.482565 2785299 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517440.482567 2785299 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517440.482568 2785299 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:10:40.485687: 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 00:00:1762517442.754458 2785299 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517445.794935 2785431 service.cc:152] XLA service 0x7c1df001ad40 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517445.794989 2785431 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:10:45.865518: 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 00:00:1762517446.289834 2785431 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517448.799226 2785431 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42:53[0m 5s/step - accuracy: 0.0625 - loss: 3.3300
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0767 - loss: 3.3314    
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0778 - loss: 3.3332
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0796 - loss: 3.3234
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0810 - loss: 3.3120
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0832 - loss: 3.2996
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0849 - loss: 3.2887
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0862 - loss: 3.2770
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0874 - loss: 3.2651
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0886 - loss: 3.2546
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0897 - loss: 3.2455
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0912 - loss: 3.2354
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0925 - loss: 3.2262
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0936 - loss: 3.2189
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0948 - loss: 3.2099
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0958 - loss: 3.2019
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0968 - loss: 3.1947
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0977 - loss: 3.1884
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0988 - loss: 3.1811
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0999 - loss: 3.1735
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1009 - loss: 3.1668
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1019 - loss: 3.1600
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1029 - loss: 3.1535
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1038 - loss: 3.1472
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1047 - loss: 3.1413
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1056 - loss: 3.1361
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1065 - loss: 3.1302
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1074 - loss: 3.1244
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1083 - loss: 3.1185
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1090 - loss: 3.1137
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1099 - loss: 3.1081
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1108 - loss: 3.1026
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1116 - loss: 3.0972
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1124 - loss: 3.0926
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1131 - loss: 3.0882
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1139 - loss: 3.0832
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1147 - loss: 3.0784
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1155 - loss: 3.0738
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1162 - loss: 3.0693
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1169 - loss: 3.0649
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1176 - loss: 3.0606
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1183 - loss: 3.0562
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1187 - loss: 3.0536
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 5ms/step - accuracy: 0.1187 - loss: 3.0535 - val_accuracy: 0.2349 - val_loss: 2.4328
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.1250 - loss: 2.9553
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1633 - loss: 2.6434  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1663 - loss: 2.6477
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1686 - loss: 2.6473
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1721 - loss: 2.6446
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1751 - loss: 2.6426
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1773 - loss: 2.6411
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6400
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6405
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6410
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1776 - loss: 2.6409
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.6406
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.6402
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1770 - loss: 2.6397
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1770 - loss: 2.6389
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1771 - loss: 2.6379
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1772 - loss: 2.6368
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.6354
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1777 - loss: 2.6339
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6324
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1782 - loss: 2.6310
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.6295
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1787 - loss: 2.6280
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1788 - loss: 2.6267
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1790 - loss: 2.6256
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.6244
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.6232
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6220
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6208
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1800 - loss: 2.6194
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.6181
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1805 - loss: 2.6166
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1807 - loss: 2.6155
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1809 - loss: 2.6141
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1812 - loss: 2.6127
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1814 - loss: 2.6115
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1816 - loss: 2.6102
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1817 - loss: 2.6092
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1819 - loss: 2.6081
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1821 - loss: 2.6069
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6058
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1825 - loss: 2.6048
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6040 - val_accuracy: 0.2708 - val_loss: 2.2986
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3750 - loss: 2.2744
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2419 - loss: 2.4752  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2362 - loss: 2.4663
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2297 - loss: 2.4629
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2258 - loss: 2.4599
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2228 - loss: 2.4616
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2209 - loss: 2.4625
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2195 - loss: 2.4629
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4633
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2173 - loss: 2.4638
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4646
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2156 - loss: 2.4656
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2148 - loss: 2.4663
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2142 - loss: 2.4668
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2136 - loss: 2.4672
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2129 - loss: 2.4677
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.4683
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2119 - loss: 2.4688
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2115 - loss: 2.4689
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2110 - loss: 2.4689
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2107 - loss: 2.4688
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2104 - loss: 2.4686
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2102 - loss: 2.4683
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2100 - loss: 2.4680
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2098 - loss: 2.4678
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2097 - loss: 2.4675
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2096 - loss: 2.4672
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2095 - loss: 2.4670
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2094 - loss: 2.4668
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2094 - loss: 2.4666
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2093 - loss: 2.4663
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2093 - loss: 2.4660
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2093 - loss: 2.4657
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2094 - loss: 2.4654
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2094 - loss: 2.4651
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2094 - loss: 2.4648
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2095 - loss: 2.4644
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2095 - loss: 2.4640
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2096 - loss: 2.4636
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2097 - loss: 2.4631
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2097 - loss: 2.4627
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2098 - loss: 2.4623
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2099 - loss: 2.4620
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2099 - loss: 2.4619 - val_accuracy: 0.2768 - val_loss: 2.2485
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.2885
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1976 - loss: 2.4450  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2029 - loss: 2.4403
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2042 - loss: 2.4387
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2042 - loss: 2.4361
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2053 - loss: 2.4320
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2065 - loss: 2.4293
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2079 - loss: 2.4268
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2093 - loss: 2.4244
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2103 - loss: 2.4225
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2107 - loss: 2.4219
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2111 - loss: 2.4213
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2116 - loss: 2.4208
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2118 - loss: 2.4207
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2121 - loss: 2.4206
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.4199
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2129 - loss: 2.4187
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2134 - loss: 2.4174
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2139 - loss: 2.4163
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2142 - loss: 2.4152
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2146 - loss: 2.4144
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2149 - loss: 2.4136
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2153 - loss: 2.4128
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2156 - loss: 2.4121
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2159 - loss: 2.4114
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4107
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4100
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2167 - loss: 2.4094
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2170 - loss: 2.4088
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2172 - loss: 2.4081
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2174 - loss: 2.4074
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4067
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4060
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2179 - loss: 2.4055
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2181 - loss: 2.4050
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4045
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4041
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4037
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4032
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4028
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4024
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2190 - loss: 2.4019
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2191 - loss: 2.4015
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2191 - loss: 2.4014 - val_accuracy: 0.2912 - val_loss: 2.2099
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1250 - loss: 2.3012
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2151 - loss: 2.2442  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2221 - loss: 2.2991
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2263 - loss: 2.3162
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3231
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2285 - loss: 2.3286
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3332
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3363
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3392
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3412
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3432
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3445
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3452
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3458
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3463
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2297 - loss: 2.3464
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2298 - loss: 2.3464
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2300 - loss: 2.3462
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2302 - loss: 2.3460
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3457
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3454
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3451
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3449
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3446
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3444
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3442
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3439
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3436
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3434
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2305 - loss: 2.3432
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2306 - loss: 2.3429
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2306 - loss: 2.3427
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2308 - loss: 2.3424
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2309 - loss: 2.3420
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2311 - loss: 2.3417
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2312 - loss: 2.3413
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2313 - loss: 2.3411
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2314 - loss: 2.3408
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2316 - loss: 2.3405
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3402
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3400
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3397
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3394
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3392
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3391 - val_accuracy: 0.3030 - val_loss: 2.1881
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.4375 - loss: 2.0112
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2760 - loss: 2.2683  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2745 - loss: 2.2557
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2715 - loss: 2.2567
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2690 - loss: 2.2560
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2666 - loss: 2.2563
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2653 - loss: 2.2571
[1m 179/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2651 - loss: 2.2569
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2642 - loss: 2.2567
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2632 - loss: 2.2562
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2624 - loss: 2.2564
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2567
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2610 - loss: 2.2574
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2587
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2600
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2611
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2622
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2635
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.2645
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2655
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2566 - loss: 2.2660
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2667
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2674
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2682
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2689
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2696
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2702
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2708
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2714
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2718
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2720
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2722
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2723
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2724
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2726
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2728
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2730
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2731
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2733
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2734
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2735
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2736
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2737
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2738
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2738 - val_accuracy: 0.3069 - val_loss: 2.1683
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 2.0807
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2238 - loss: 2.3728  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2262 - loss: 2.3508
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3265
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2357 - loss: 2.3129
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2377 - loss: 2.3059
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2399 - loss: 2.2989
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2415 - loss: 2.2939
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2899
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2440 - loss: 2.2863
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2453 - loss: 2.2825
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2789
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.2756
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.2729
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2500 - loss: 2.2709
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.2689
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2515 - loss: 2.2674
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2521 - loss: 2.2664
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2528 - loss: 2.2654
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2533 - loss: 2.2645
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2635
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2627
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2619
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2613
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2607
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2602
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2596
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2565 - loss: 2.2590
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2586
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2570 - loss: 2.2583
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2571 - loss: 2.2579
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2573 - loss: 2.2576
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2573
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2570
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2576 - loss: 2.2567
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2565
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2563
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2561
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2559
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2556
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2580 - loss: 2.2553
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2580 - loss: 2.2550
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2546
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2545 - val_accuracy: 0.3119 - val_loss: 2.1584
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2661
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3149 - loss: 2.1672  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1742
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1848
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1941
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.2025
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2773 - loss: 2.2082
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2754 - loss: 2.2138
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2739 - loss: 2.2183
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.2214
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2713 - loss: 2.2229
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2700 - loss: 2.2239
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2690 - loss: 2.2242
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2682 - loss: 2.2245
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.2246
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2673 - loss: 2.2247
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.2248
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2668 - loss: 2.2248
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2666 - loss: 2.2247
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2665 - loss: 2.2246
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2663 - loss: 2.2244
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2663 - loss: 2.2241
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2662 - loss: 2.2240
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2662 - loss: 2.2238
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2662 - loss: 2.2235
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2662 - loss: 2.2231
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2662 - loss: 2.2227
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2662 - loss: 2.2224
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2662 - loss: 2.2219
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.2215
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.2211
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.2207
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.2204
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.2201
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2199
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2197
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2194
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2191
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2189
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2187
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2186
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2184
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2182
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2659 - loss: 2.2181 - val_accuracy: 0.3202 - val_loss: 2.1513
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9973
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2731 - loss: 2.1412  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1281
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1236
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1226
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1241
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1266
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1305
[1m 207/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1331
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1362
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1382
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1401
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1421
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1437
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1452
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1466
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1482
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1496
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1513
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1530
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1544
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1558
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1568
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1578
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1587
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1595
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1602
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1606
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1611
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1615
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1619
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1622
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1626
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1628
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1632
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1636
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1639
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1643
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1646
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1650
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1653
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1657
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1660
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1662
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1663 - val_accuracy: 0.3250 - val_loss: 2.1407
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2472
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2296 - loss: 2.2131  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2449 - loss: 2.2050
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2534 - loss: 2.1957
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2588 - loss: 2.1868
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2623 - loss: 2.1799
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2653 - loss: 2.1750
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.1712
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2691 - loss: 2.1689
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2701 - loss: 2.1678
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.1670
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2718 - loss: 2.1664
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2724 - loss: 2.1659
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2729 - loss: 2.1654
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.1651
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2737 - loss: 2.1648
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2739 - loss: 2.1644
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2742 - loss: 2.1641
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2744 - loss: 2.1638
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2745 - loss: 2.1636
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2746 - loss: 2.1637
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2746 - loss: 2.1638
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2746 - loss: 2.1638
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2747 - loss: 2.1638
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2747 - loss: 2.1639
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2748 - loss: 2.1640
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2749 - loss: 2.1640
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2749 - loss: 2.1640
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2750 - loss: 2.1640
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2752 - loss: 2.1639
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2753 - loss: 2.1639
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2755 - loss: 2.1637
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2756 - loss: 2.1636
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1634
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2760 - loss: 2.1633
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2761 - loss: 2.1631
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2763 - loss: 2.1630
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1628
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1625
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1624
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1622
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1621
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1620
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1620 - val_accuracy: 0.3105 - val_loss: 2.1265
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.6437
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1868  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2895 - loss: 2.1860
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1811
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1822
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1826
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1835
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1846
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1849
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1839
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1825
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1810
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1795
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1780
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1766
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1751
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1735
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 2.1721
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1708
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1695
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1685
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1673
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1660
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1650
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1640
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1629
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1619
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1612
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1604
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1595
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1588
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1582
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1575
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1568
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1562
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1556
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1552
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1547
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1542
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1538
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1534
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1529
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1525
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1524 - val_accuracy: 0.3395 - val_loss: 2.0992
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3473
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2424 - loss: 2.2086  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2580 - loss: 2.1836
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2679 - loss: 2.1682
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2747 - loss: 2.1558
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1490
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1450
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1410
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1379
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1362
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1347
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1336
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1325
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1314
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2880 - loss: 2.1306
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1301
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1298
[1m 476/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2886 - loss: 2.1295
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1292
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1290
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1289
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1287
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1283
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1280
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2895 - loss: 2.1276
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1272
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2899 - loss: 2.1269
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2901 - loss: 2.1264
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2903 - loss: 2.1260
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2904 - loss: 2.1256
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2906 - loss: 2.1252
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2907 - loss: 2.1248
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2909 - loss: 2.1245
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2911 - loss: 2.1241
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2912 - loss: 2.1238
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1235
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2915 - loss: 2.1232
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2916 - loss: 2.1230
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2917 - loss: 2.1228
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1226
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1224
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1222
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1221
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1221 - val_accuracy: 0.3367 - val_loss: 2.1160
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.3366
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2617 - loss: 2.0715  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2700 - loss: 2.0856
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2781 - loss: 2.0832
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2815 - loss: 2.0828
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2840 - loss: 2.0824
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2855 - loss: 2.0826
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 2.0841
[1m 207/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2883 - loss: 2.0850
[1m 233/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2896 - loss: 2.0857
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2909 - loss: 2.0868
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2918 - loss: 2.0877
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.0886
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.0893
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2929 - loss: 2.0901
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2931 - loss: 2.0906
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 2.0909
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2936 - loss: 2.0911
[1m 476/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 2.0914
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 2.0917
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.0920
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 2.0922
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2948 - loss: 2.0924
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2950 - loss: 2.0927
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 2.0930
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 2.0932
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 2.0934
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2958 - loss: 2.0936
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 2.0939
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0941
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2961 - loss: 2.0944
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2962 - loss: 2.0946
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2962 - loss: 2.0948
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2963 - loss: 2.0951
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 2.0952
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 2.0954
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2966 - loss: 2.0956
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2967 - loss: 2.0958
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2967 - loss: 2.0960
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 2.0962
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 2.0964
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 2.0965
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.0966
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2971 - loss: 2.0967
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2971 - loss: 2.0967 - val_accuracy: 0.3282 - val_loss: 2.1149
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.0000e+00 - loss: 2.7129
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2465 - loss: 2.2396      
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2734 - loss: 2.1838
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2782 - loss: 2.1677
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1576
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1505
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2869 - loss: 2.1465
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1438
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1412
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1384
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2900 - loss: 2.1357
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2904 - loss: 2.1339
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2907 - loss: 2.1321
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2909 - loss: 2.1308
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2912 - loss: 2.1293
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1281
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2916 - loss: 2.1266
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1254
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1238
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1224
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1211
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1198
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1188
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1179
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1170
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1161
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2948 - loss: 2.1153
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1145
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1136
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1128
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1120
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1113
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 2.1105
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2966 - loss: 2.1098
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1090
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2971 - loss: 2.1084
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1076
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2976 - loss: 2.1070
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1063
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1056
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1050
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1043
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1037
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 2.1031
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1031 - val_accuracy: 0.3415 - val_loss: 2.1167
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.7511
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3591 - loss: 1.9652  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3328 - loss: 2.0179
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0357
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0473
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0534
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0556
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0570
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0575
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0579
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0592
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0607
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0619
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0627
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0633
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0635
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0636
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0637
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0639
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0643
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0645
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0647
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0647
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0647
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0646
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0646
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0645
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0642
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0640
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0637
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0634
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0632
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0629
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0625
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0621
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0619
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0616
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0614
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0611
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0609
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0608
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0607
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0606
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0606 - val_accuracy: 0.3323 - val_loss: 2.1232
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9580
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0663  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0604
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0588
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0580
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0566
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0555
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0542
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0536
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0528
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0521
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0511
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0499
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0487
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0477
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0468
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 2.0458
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 2.0449
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 2.0441
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0436
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0430
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0428
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0425
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0421
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0420
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 2.0419
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 2.0419
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0419
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0420
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0422
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 2.0424
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 2.0426
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0428
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0429
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0429
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0430
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0430
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3177 - loss: 2.0431
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3177 - loss: 2.0432
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0432
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0433
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0433
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0433
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0432 - val_accuracy: 0.3353 - val_loss: 2.0984
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.0625 - loss: 2.5002
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2460 - loss: 2.1449  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2811 - loss: 2.0739
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.0581
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 2.0521
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0469
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0443
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 2.0432
[1m 230/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3083 - loss: 2.0439
[1m 255/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0442
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0443
[1m 310/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0438
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0427
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0411
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0397
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0385
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 2.0373
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0362
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0352
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0344
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3188 - loss: 2.0336
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0328
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0322
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0318
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0314
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0311
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0309
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0308
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0306
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0305
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3215 - loss: 2.0304
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0303
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0302
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0301
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0300
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0299
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0299
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0298
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0298
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0297
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0296
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0296 - val_accuracy: 0.3363 - val_loss: 2.0851
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3704
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2898 - loss: 2.0423  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3011 - loss: 2.0209
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0234
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0212
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3076 - loss: 2.0195
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0191
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0178
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0166
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0157
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3162 - loss: 2.0143
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0139
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0133
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0123
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0112
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0103
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0095
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0089
[1m 470/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0084
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0080
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0077
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0074
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0073
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0072
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0070
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0069
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0068
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0067
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0067
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0068
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0069
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0071
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0073
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0075
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0076
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0078
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0080
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0083
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0085
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0087
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0089
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0090
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0091
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0092 - val_accuracy: 0.3206 - val_loss: 2.1050
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3496
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0488  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0437
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0391
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3238 - loss: 2.0338
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0275
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0234
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3284 - loss: 2.0189
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 2.0163
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3286 - loss: 2.0148
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3282 - loss: 2.0138
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0132
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0122
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0118
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3272 - loss: 2.0115
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0113
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0111
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0107
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0100
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0093
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0087
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0082
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0078
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0075
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0072
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0069
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0065
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3272 - loss: 2.0062
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0060
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0057
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0055
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0053
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0052
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0050
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0049
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0047
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3278 - loss: 2.0046
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3278 - loss: 2.0044
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3279 - loss: 2.0043
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3279 - loss: 2.0042
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0040
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0039
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0037
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0037 - val_accuracy: 0.3331 - val_loss: 2.1105
Epoch 20/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2829
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2661 - loss: 2.0419  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2900 - loss: 2.0129
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2984 - loss: 2.0028
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3057 - loss: 1.9912
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3113 - loss: 1.9860
[1m 152/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3147 - loss: 1.9839
[1m 179/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3176 - loss: 1.9832
[1m 206/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 1.9828
[1m 231/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 1.9821
[1m 257/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3223 - loss: 1.9816
[1m 284/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3232 - loss: 1.9818
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 1.9823
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 1.9831
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3253 - loss: 1.9836
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3258 - loss: 1.9838
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 1.9838
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3269 - loss: 1.9836
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3274 - loss: 1.9835
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3278 - loss: 1.9834
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3283 - loss: 1.9831
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 1.9829
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 1.9828
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 1.9827
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 1.9826
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 1.9826
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 1.9827
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 1.9828
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3313 - loss: 1.9829
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 1.9831
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3317 - loss: 1.9833
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3319 - loss: 1.9835
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3321 - loss: 1.9836
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3323 - loss: 1.9836
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3324 - loss: 1.9837
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3325 - loss: 1.9838
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3327 - loss: 1.9838
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3328 - loss: 1.9838
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3330 - loss: 1.9838
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3331 - loss: 1.9839
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3332 - loss: 1.9839
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3334 - loss: 1.9839
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.9839
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9839 - val_accuracy: 0.3401 - val_loss: 2.1163
Epoch 21/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2508
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2860 - loss: 2.0071  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3125 - loss: 1.9672
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 1.9597
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3215 - loss: 1.9628
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9662
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 1.9687
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3262 - loss: 1.9702
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3275 - loss: 1.9710
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 1.9718
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3294 - loss: 1.9723
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3303 - loss: 1.9729
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 1.9730
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9729
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 1.9730
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 1.9726
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3343 - loss: 1.9723
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3348 - loss: 1.9722
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3352 - loss: 1.9720
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3356 - loss: 1.9718
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3360 - loss: 1.9716
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3364 - loss: 1.9714
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3368 - loss: 1.9712
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3371 - loss: 1.9710
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3373 - loss: 1.9707
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.9705
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.9703
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9703
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.9702
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3381 - loss: 1.9701
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 1.9700
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3383 - loss: 1.9699
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3384 - loss: 1.9699
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3385 - loss: 1.9698
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3386 - loss: 1.9697
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 1.9697
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3388 - loss: 1.9696
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.9696
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.9695
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9694
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.9693
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.9692
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3392 - loss: 1.9692 - val_accuracy: 0.3302 - val_loss: 2.1460
Epoch 22/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7720
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3673 - loss: 1.8959  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3426 - loss: 1.9500
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3387 - loss: 1.9604
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.9672
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.9697
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9680
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3394 - loss: 1.9654
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3404 - loss: 1.9636
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3415 - loss: 1.9615
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.9603
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.9591
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 1.9577
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3435 - loss: 1.9565
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 1.9559
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.9557
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3440 - loss: 1.9555
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3441 - loss: 1.9553
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3441 - loss: 1.9551
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3442 - loss: 1.9549
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3443 - loss: 1.9546
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9545
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3445 - loss: 1.9545
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3445 - loss: 1.9547
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3445 - loss: 1.9548
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3445 - loss: 1.9550
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9551
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9551
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9552
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3443 - loss: 1.9553
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3443 - loss: 1.9554
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9554
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9554
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9554
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3443 - loss: 1.9555
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9556
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9556
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9556
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3445 - loss: 1.9556
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3445 - loss: 1.9556
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3445 - loss: 1.9556
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3446 - loss: 1.9556
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3446 - loss: 1.9556
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3446 - loss: 1.9556 - val_accuracy: 0.3218 - val_loss: 2.1483

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 654ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 962us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:06[0m 843ms/step
[1m 52/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 989us/step  
[1m106/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 959us/step
[1m164/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 925us/step
[1m216/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 936us/step
[1m274/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 921us/step
[1m323/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 938us/step
[1m372/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 951us/step
[1m427/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 946us/step
[1m486/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 936us/step
[1m540/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 936us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 999us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 43/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m 91/158[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m147/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 34.43 [%]
Global F1 score (validation) = 33.76 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.01454237 0.01186601 0.01567305 ... 0.0200736  0.04772676 0.0098991 ]
 [0.00399645 0.00274947 0.00243444 ... 0.11035474 0.01029903 0.00329129]
 [0.00323213 0.00271967 0.0022056  ... 0.00536096 0.00174453 0.00133578]
 ...
 [0.16527899 0.0658675  0.16188395 ... 0.00847404 0.12642683 0.09208684]
 [0.15798493 0.04888432 0.11418629 ... 0.01417811 0.07667749 0.07924313]
 [0.1825691  0.06020614 0.12120155 ... 0.0153983  0.08447117 0.0716625 ]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 38.89 [%]
Global accuracy score (test) = 27.84 [%]
Global F1 score (train) = 38.89 [%]
Global F1 score (test) = 26.85 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.27      0.68      0.38       184
 CAMINAR CON MÓVIL O LIBRO       0.18      0.14      0.16       184
       CAMINAR USUAL SPEED       0.24      0.18      0.21       184
            CAMINAR ZIGZAG       0.21      0.12      0.16       184
          DE PIE BARRIENDO       0.49      0.21      0.29       184
   DE PIE DOBLANDO TOALLAS       0.35      0.21      0.26       184
    DE PIE MOVIENDO LIBROS       0.27      0.28      0.28       184
          DE PIE USANDO PC       0.08      0.07      0.07       184
        FASE REPOSO CON K5       0.34      0.68      0.45       184
INCREMENTAL CICLOERGOMETRO       0.51      0.38      0.44       184
           SENTADO LEYENDO       0.08      0.07      0.07       184
         SENTADO USANDO PC       0.19      0.19      0.19       184
      SENTADO VIENDO LA TV       0.16      0.23      0.19       184
   SUBIR Y BAJAR ESCALERAS       0.42      0.27      0.32       184
                    TROTAR       0.62      0.50      0.55       161

                  accuracy                           0.28      2737
                 macro avg       0.29      0.28      0.27      2737
              weighted avg       0.29      0.28      0.27      2737


Accuracy capturado en la ejecución 12: 27.84 [%]
F1-score capturado en la ejecución 12: 26.85 [%]

=== EJECUCIÓN 13 ===

--- TRAIN (ejecución 13) ---

--- TEST (ejecución 13) ---
2025-11-07 13:12:02.195948: 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`.
2025-11-07 13:12:02.207494: 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 00:00:1762517522.221650 2788853 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517522.225916 2788853 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517522.236042 2788853 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517522.236064 2788853 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517522.236066 2788853 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517522.236068 2788853 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:12:02.239287: 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 00:00:1762517524.543958 2788853 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517527.620366 2788958 service.cc:152] XLA service 0x78d9b0001f00 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517527.620407 2788958 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:12:07.690253: 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 00:00:1762517528.129996 2788958 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517530.655417 2788958 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:25[0m 5s/step - accuracy: 0.0625 - loss: 3.3740
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0525 - loss: 3.4127    
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0569 - loss: 3.3843
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0613 - loss: 3.3556
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0632 - loss: 3.3439
[1m 127/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0652 - loss: 3.3339
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0677 - loss: 3.3217
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0704 - loss: 3.3084
[1m 205/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0723 - loss: 3.2978
[1m 231/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0744 - loss: 3.2863
[1m 260/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0765 - loss: 3.2739
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0782 - loss: 3.2631
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0800 - loss: 3.2525
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0817 - loss: 3.2424
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0834 - loss: 3.2327
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0853 - loss: 3.2232
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0869 - loss: 3.2152
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0884 - loss: 3.2076
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0900 - loss: 3.1999
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0913 - loss: 3.1934
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0929 - loss: 3.1854
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0943 - loss: 3.1780
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0957 - loss: 3.1708
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0970 - loss: 3.1640
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0982 - loss: 3.1580
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0995 - loss: 3.1517
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1007 - loss: 3.1452
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1018 - loss: 3.1397
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1028 - loss: 3.1342
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1039 - loss: 3.1286
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1050 - loss: 3.1231
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1061 - loss: 3.1177
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1071 - loss: 3.1124
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1081 - loss: 3.1075
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1090 - loss: 3.1025
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1101 - loss: 3.0973
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1110 - loss: 3.0925
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1119 - loss: 3.0876
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1127 - loss: 3.0834
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1136 - loss: 3.0786
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1145 - loss: 3.0742
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1153 - loss: 3.0697
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1162 - loss: 3.0651
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1166 - loss: 3.0625
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1167 - loss: 3.0623 - val_accuracy: 0.2478 - val_loss: 2.3344
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.9689
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1909 - loss: 2.6610  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1907 - loss: 2.6291
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6341
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1840 - loss: 2.6383
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1825 - loss: 2.6385
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1819 - loss: 2.6380
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1812 - loss: 2.6393
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1808 - loss: 2.6413
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1802 - loss: 2.6437
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6462
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1789 - loss: 2.6484
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.6502
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6516
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.6524
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1775 - loss: 2.6529
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1773 - loss: 2.6529
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1772 - loss: 2.6528
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1772 - loss: 2.6526
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1773 - loss: 2.6522
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.6519
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1774 - loss: 2.6516
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1775 - loss: 2.6511
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1776 - loss: 2.6506
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1778 - loss: 2.6499
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6491
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1782 - loss: 2.6484
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1783 - loss: 2.6478
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1785 - loss: 2.6472
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1787 - loss: 2.6465
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1789 - loss: 2.6457
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1791 - loss: 2.6449
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.6442
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6434
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6425
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1799 - loss: 2.6416
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1801 - loss: 2.6408
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1803 - loss: 2.6401
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6393
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1806 - loss: 2.6385
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1808 - loss: 2.6376
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1810 - loss: 2.6369
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1811 - loss: 2.6361
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1812 - loss: 2.6356 - val_accuracy: 0.2599 - val_loss: 2.2584
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.6231
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1691 - loss: 2.5485  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1816 - loss: 2.5223
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1901 - loss: 2.5087
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1953 - loss: 2.5025
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1979 - loss: 2.4995
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1997 - loss: 2.4967
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2012 - loss: 2.4945
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2023 - loss: 2.4929
[1m 255/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2029 - loss: 2.4924
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2033 - loss: 2.4919
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2036 - loss: 2.4920
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2038 - loss: 2.4917
[1m 366/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2040 - loss: 2.4912
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2043 - loss: 2.4906
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.4901
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2049 - loss: 2.4895
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2051 - loss: 2.4892
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2052 - loss: 2.4890
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2054 - loss: 2.4890
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2055 - loss: 2.4888
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2056 - loss: 2.4888
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4887
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4887
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4886
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4885
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4883
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4881
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4878
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4875
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4872
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2058 - loss: 2.4869
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2059 - loss: 2.4865
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2060 - loss: 2.4861
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2061 - loss: 2.4858
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2062 - loss: 2.4854
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2062 - loss: 2.4850
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2063 - loss: 2.4847
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2063 - loss: 2.4844
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.4841
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2064 - loss: 2.4838
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2065 - loss: 2.4835
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2065 - loss: 2.4832
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2065 - loss: 2.4831 - val_accuracy: 0.2752 - val_loss: 2.2116
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.6293
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2120 - loss: 2.4844  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4678
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2210 - loss: 2.4553
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2217 - loss: 2.4487
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2209 - loss: 2.4468
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.4452
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2191 - loss: 2.4449
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4435
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4421
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4407
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2190 - loss: 2.4390
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2191 - loss: 2.4372
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4352
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4336
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4325
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4312
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2191 - loss: 2.4303
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2191 - loss: 2.4293
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4285
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4275
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4268
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4259
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2193 - loss: 2.4251
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2193 - loss: 2.4244
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4236
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4229
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2195 - loss: 2.4221
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2195 - loss: 2.4215
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2195 - loss: 2.4210
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4205
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4200
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4197
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4193
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4190
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4187
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4183
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4179
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4175
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4171
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2195 - loss: 2.4167
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2195 - loss: 2.4164
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2195 - loss: 2.4161
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2196 - loss: 2.4159 - val_accuracy: 0.2936 - val_loss: 2.1692
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0000e+00 - loss: 2.6369
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1979 - loss: 2.3437      
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2106 - loss: 2.3426
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2200 - loss: 2.3335
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2251 - loss: 2.3300
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3296
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3282
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3280
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2335 - loss: 2.3295
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3311
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3330
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2327 - loss: 2.3349
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3360
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2314 - loss: 2.3373
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2308 - loss: 2.3386
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2303 - loss: 2.3399
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2300 - loss: 2.3409
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2298 - loss: 2.3417
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3423
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2294 - loss: 2.3430
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2292 - loss: 2.3436
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2291 - loss: 2.3441
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3446
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3449
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3450
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3452
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3453
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3455
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3457
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3459
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3461
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3463
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2291 - loss: 2.3466
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2291 - loss: 2.3468
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2291 - loss: 2.3470
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2292 - loss: 2.3471
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2292 - loss: 2.3473
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2293 - loss: 2.3474
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2294 - loss: 2.3475
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3476
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3477
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3478
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3478 - val_accuracy: 0.3034 - val_loss: 2.1624
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.3979
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2734  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2964
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2528 - loss: 2.2957
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2501 - loss: 2.2993
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2481 - loss: 2.3006
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3033
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2449 - loss: 2.3062
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2437 - loss: 2.3083
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2430 - loss: 2.3091
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.3093
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3098
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2426 - loss: 2.3095
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2426 - loss: 2.3091
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2426 - loss: 2.3082
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.3075
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.3072
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3071
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3069
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3068
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.3067
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.3066
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.3064
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.3062
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3060
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3058
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3056
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3054
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3052
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3049
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3046
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3043
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3040
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3037
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3034
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3031
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.3028
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.3025
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.3022
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.3019
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.3017
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.3014
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2436 - loss: 2.3013 - val_accuracy: 0.3073 - val_loss: 2.1266
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4048
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2402 - loss: 2.2748  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2666
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2529 - loss: 2.2623
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2584
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2598
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2605
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2609
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2610
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2612
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2622
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2637
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2651
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2668
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2678
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2685
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2689
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2690
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2687
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2684
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2681
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2678
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2675
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2672
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2669
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2667
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2665
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2663
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2662
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2661
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2660
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2659
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2658
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2656
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2655
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2653
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2652
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2651
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2650
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2650
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2650
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2649
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2648
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2648 - val_accuracy: 0.3248 - val_loss: 2.1088
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3805
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3081  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2390 - loss: 2.2841
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2453 - loss: 2.2754
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2502 - loss: 2.2711
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2524 - loss: 2.2681
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2663
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2655
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2565 - loss: 2.2647
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2570 - loss: 2.2640
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2631
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2625
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2614
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2601
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2588
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2578
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2568
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2562
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2557
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2551
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2546
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2542
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2537
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2530
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2525
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2521
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2518
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2515
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2512
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2509
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2506
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2504
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2502
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2499
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2496
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2493
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2490
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2488
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2485
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2482
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2479
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2476
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2473
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2470
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2470 - val_accuracy: 0.3061 - val_loss: 2.1332
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9843
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1876  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2687 - loss: 2.1966
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2685 - loss: 2.1984
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2701 - loss: 2.1992
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.1969
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.1966
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2717 - loss: 2.1976
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.1982
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2712 - loss: 2.1991
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2711 - loss: 2.1994
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.1996
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.1997
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2711 - loss: 2.1995
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2712 - loss: 2.1993
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2712 - loss: 2.1989
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2713 - loss: 2.1987
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.1985
[1m 482/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2718 - loss: 2.1982
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2720 - loss: 2.1980
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2721 - loss: 2.1978
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2723 - loss: 2.1975
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2724 - loss: 2.1974
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1972
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1972
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1972
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1970
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2728 - loss: 2.1969
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 2.1968
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1967
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2732 - loss: 2.1965
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2732 - loss: 2.1965
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2732 - loss: 2.1965
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2732 - loss: 2.1967
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2731 - loss: 2.1968
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2731 - loss: 2.1969
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1970
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1970
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1971
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1971
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1971
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1971
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1971
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1971 - val_accuracy: 0.3327 - val_loss: 2.1005
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1237
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2591 - loss: 2.1877  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2621 - loss: 2.1908
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2631 - loss: 2.1913
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2661 - loss: 2.1875
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2669 - loss: 2.1874
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2681 - loss: 2.1854
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2694 - loss: 2.1827
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2707 - loss: 2.1798
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2717 - loss: 2.1779
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 2.1762
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2737 - loss: 2.1748
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2745 - loss: 2.1737
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2751 - loss: 2.1728
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2755 - loss: 2.1723
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1719
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2761 - loss: 2.1717
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2763 - loss: 2.1717
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1718
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1720
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1724
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1727
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1730
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1734
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1737
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1739
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1741
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1744
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1746
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1748
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1751
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1753
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1754
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1755
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1755
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1754
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1754
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1754
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1753
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1752
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1752
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1751
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1751
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1751 - val_accuracy: 0.3345 - val_loss: 2.0810
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.1246
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2746 - loss: 2.1566  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1503
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2742 - loss: 2.1528
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1568
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.1589
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2745 - loss: 2.1611
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2757 - loss: 2.1623
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1626
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1628
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1630
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1628
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1624
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1623
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1621
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1621
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1621
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1622
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1623
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1625
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1625
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1625
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1623
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1620
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1617
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1613
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1610
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1607
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1605
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1602
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1600
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1597
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1594
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1591
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1588
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1586
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1584
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1582
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1580
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1578
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1576
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1574
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1572
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1571 - val_accuracy: 0.3256 - val_loss: 2.0911
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2505
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2461 - loss: 2.2613  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2638 - loss: 2.2237
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.2065
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2762 - loss: 2.1959
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1891
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1833
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1790
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1762
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1738
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1717
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1698
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1685
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1678
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1674
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1672
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1669
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1666
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1664
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1663
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1660
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1655
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1651
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1646
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1641
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1635
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1628
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1622
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1617
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1610
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1605
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1600
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1594
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1588
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1583
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1578
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1573
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1568
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1564
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1560
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1555
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1551
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1547 - val_accuracy: 0.3210 - val_loss: 2.0918
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.8045
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0468  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0942
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3090 - loss: 2.1055
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3070 - loss: 2.1093
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3055 - loss: 2.1132
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 2.1141
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 2.1154
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 2.1163
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 2.1172
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 2.1172
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 2.1174
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1177
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1179
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1180
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1178
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1176
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 2.1173
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1172
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1173
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1173
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1171
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1169
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1167
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1165
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1163
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1161
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1159
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1158
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1157
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1156
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1156
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3000 - loss: 2.1155
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1155
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1156
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1156
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1156
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1156
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1156
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1155
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1154
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1152
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1151 - val_accuracy: 0.3151 - val_loss: 2.0933
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0205
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1485  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1671
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1663
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1597
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1554
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1506
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1453
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1411
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1373
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1339
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2875 - loss: 2.1313
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1288
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1268
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1250
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1233
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1218
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1204
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2900 - loss: 2.1189
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2904 - loss: 2.1174
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2907 - loss: 2.1161
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2910 - loss: 2.1149
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2912 - loss: 2.1139
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2915 - loss: 2.1128
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1118
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1108
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1099
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1090
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1081
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 2.1072
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1063
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1056
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1048
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1042
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1035
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1029
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1024
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1019
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1015
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2948 - loss: 2.1011
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1007
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1003
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 2.0999
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2953 - loss: 2.0998 - val_accuracy: 0.3478 - val_loss: 2.0555
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8342
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1176  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1183
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1175
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2910 - loss: 2.1140
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1108
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2948 - loss: 2.1088
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.1065
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1045
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2976 - loss: 2.1026
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1008
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2989 - loss: 2.0989
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 2.0972
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 2.0958
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.0946
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0936
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0929
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.0920
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0911
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3015 - loss: 2.0901
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0894
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3018 - loss: 2.0888
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0882
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0876
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0869
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0862
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0857
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0852
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0849
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0846
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0843
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0840
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0837
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0834
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0831
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3033 - loss: 2.0828
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3033 - loss: 2.0825
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0822
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0818
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0815
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0811
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0809
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0806
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0806 - val_accuracy: 0.3431 - val_loss: 2.1012
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4479
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3080 - loss: 2.1210  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2978 - loss: 2.0980
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2981 - loss: 2.0875
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3015 - loss: 2.0759
[1m 127/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0697
[1m 153/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3049 - loss: 2.0646
[1m 179/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0637
[1m 207/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0627
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 2.0615
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0606
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0605
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0604
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0599
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0590
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0582
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0576
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0571
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0566
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0564
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 2.0564
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 2.0565
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0566
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3079 - loss: 2.0568
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3081 - loss: 2.0570
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3083 - loss: 2.0572
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0573
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3086 - loss: 2.0574
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0574
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0573
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0572
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0571
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0571
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0571
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0571
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0570
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0570
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0570
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0570
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0570
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0570
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0571
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0571
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0571
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0571 - val_accuracy: 0.3375 - val_loss: 2.0821
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.6250 - loss: 1.5190
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3860 - loss: 1.9583  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3540 - loss: 2.0208
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3393 - loss: 2.0464
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 2.0507
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0503
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 2.0486
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0472
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0460
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0452
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0450
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0447
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0442
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0435
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0430
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0424
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0420
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0418
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0416
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0413
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0410
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0407
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0406
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0406
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0404
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0403
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0402
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0402
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0401
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0400
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0399
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0398
[1m 873/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0398
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0398
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0398
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0398
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3215 - loss: 2.0398
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3215 - loss: 2.0399
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0399
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0399
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0399
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0399
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0397
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0397 - val_accuracy: 0.3399 - val_loss: 2.0762
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.8345
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3574 - loss: 1.9849  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0387
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0536
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0543
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0536
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0529
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0528
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0530
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0526
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0520
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0512
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0502
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0494
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0485
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0478
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0475
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0470
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0466
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0461
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0457
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0453
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0449
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3158 - loss: 2.0444
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3162 - loss: 2.0440
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3165 - loss: 2.0436
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0432
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0429
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0426
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0423
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0419
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3180 - loss: 2.0416
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0412
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 2.0408
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3187 - loss: 2.0404
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 2.0400
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0395
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0390
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0385
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0380
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0375
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0370
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0365
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0361 - val_accuracy: 0.3365 - val_loss: 2.1096
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3830
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3317 - loss: 2.0937  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0516
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 2.0255
[1m 118/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0131
[1m 148/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3326 - loss: 2.0057
[1m 176/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 2.0014
[1m 205/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3332 - loss: 1.9986
[1m 233/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3330 - loss: 1.9977
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3328 - loss: 1.9971
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.9972
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9976
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.9978
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 1.9977
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 1.9976
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 1.9976
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 1.9977
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 1.9976
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 1.9973
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9970
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9968
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3321 - loss: 1.9965
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3321 - loss: 1.9964
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3322 - loss: 1.9963
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3322 - loss: 1.9962
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3322 - loss: 1.9962
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3322 - loss: 1.9962
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3322 - loss: 1.9961
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3321 - loss: 1.9962
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3321 - loss: 1.9962
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9961
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9960
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9959
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9958
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9958
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9958
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9959
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9959
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9960
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3319 - loss: 1.9961
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3319 - loss: 1.9962
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3319 - loss: 1.9963
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3319 - loss: 1.9964 - val_accuracy: 0.3278 - val_loss: 2.0706

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 644ms/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:02[0m 836ms/step
[1m 53/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 974us/step  
[1m112/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 911us/step
[1m162/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 941us/step
[1m216/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 940us/step
[1m271/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 935us/step
[1m325/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 936us/step
[1m381/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 931us/step
[1m440/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 921us/step
[1m491/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 928us/step
[1m544/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 930us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 53/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 973us/step
[1m106/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 960us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 32.18 [%]
Global F1 score (validation) = 31.84 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.03622795 0.01213574 0.02378311 ... 0.01719899 0.08616622 0.01854141]
 [0.00226841 0.0015558  0.00123378 ... 0.12980251 0.0073105  0.00325871]
 [0.00138719 0.00093665 0.00103579 ... 0.00338913 0.00071941 0.00041364]
 ...
 [0.13915147 0.06401107 0.16909613 ... 0.00105476 0.24147584 0.11107442]
 [0.18814602 0.0706913  0.12504789 ... 0.00401694 0.12237562 0.17699988]
 [0.16096495 0.07272639 0.15272923 ... 0.00580816 0.20284094 0.09475385]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 40.11 [%]
Global accuracy score (test) = 29.45 [%]
Global F1 score (train) = 39.95 [%]
Global F1 score (test) = 29.43 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.28      0.51      0.36       184
 CAMINAR CON MÓVIL O LIBRO       0.27      0.25      0.26       184
       CAMINAR USUAL SPEED       0.31      0.13      0.18       184
            CAMINAR ZIGZAG       0.35      0.22      0.27       184
          DE PIE BARRIENDO       0.27      0.25      0.26       184
   DE PIE DOBLANDO TOALLAS       0.32      0.33      0.33       184
    DE PIE MOVIENDO LIBROS       0.30      0.32      0.31       184
          DE PIE USANDO PC       0.12      0.15      0.13       184
        FASE REPOSO CON K5       0.56      0.54      0.55       184
INCREMENTAL CICLOERGOMETRO       0.62      0.34      0.44       184
           SENTADO LEYENDO       0.23      0.11      0.15       184
         SENTADO USANDO PC       0.19      0.22      0.20       184
      SENTADO VIENDO LA TV       0.14      0.20      0.16       184
   SUBIR Y BAJAR ESCALERAS       0.30      0.40      0.34       184
                    TROTAR       0.46      0.47      0.47       161

                  accuracy                           0.29      2737
                 macro avg       0.31      0.30      0.29      2737
              weighted avg       0.31      0.29      0.29      2737


Accuracy capturado en la ejecución 13: 29.45 [%]
F1-score capturado en la ejecución 13: 29.43 [%]

=== EJECUCIÓN 14 ===

--- TRAIN (ejecución 14) ---

--- TEST (ejecución 14) ---
2025-11-07 13:13:16.117777: 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`.
2025-11-07 13:13:16.129044: 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 00:00:1762517596.142490 2792025 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517596.146780 2792025 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517596.156929 2792025 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517596.156948 2792025 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517596.156951 2792025 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517596.156954 2792025 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:13:16.159975: 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 00:00:1762517598.440629 2792025 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517601.472049 2792154 service.cc:152] XLA service 0x755054019f70 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517601.472086 2792154 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:13:21.540677: 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 00:00:1762517601.963386 2792154 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517604.477676 2792154 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43:00[0m 5s/step - accuracy: 0.0625 - loss: 3.3703
[1m  18/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0854 - loss: 3.3546    
[1m  47/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0835 - loss: 3.3283
[1m  72/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0799 - loss: 3.3165
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0775 - loss: 3.3031
[1m 126/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0769 - loss: 3.2938
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0769 - loss: 3.2850
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0773 - loss: 3.2757
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0777 - loss: 3.2664
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0782 - loss: 3.2578
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0789 - loss: 3.2488
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0797 - loss: 3.2401
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0806 - loss: 3.2308
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0817 - loss: 3.2218
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0828 - loss: 3.2138
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0838 - loss: 3.2061
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0850 - loss: 3.1985
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0859 - loss: 3.1916
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0869 - loss: 3.1841
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0879 - loss: 3.1772
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0891 - loss: 3.1699
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0902 - loss: 3.1627
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0913 - loss: 3.1564
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0924 - loss: 3.1500
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0935 - loss: 3.1432
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0945 - loss: 3.1373
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0957 - loss: 3.1305
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0968 - loss: 3.1244
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0979 - loss: 3.1187
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0988 - loss: 3.1134
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0997 - loss: 3.1080
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1006 - loss: 3.1032
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1014 - loss: 3.0982
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1022 - loss: 3.0936
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1031 - loss: 3.0884
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1039 - loss: 3.0838
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1047 - loss: 3.0789
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1056 - loss: 3.0740
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1064 - loss: 3.0691
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1072 - loss: 3.0648
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1080 - loss: 3.0602
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1088 - loss: 3.0559
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1095 - loss: 3.0516
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1097 - loss: 3.0508
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1097 - loss: 3.0506 - val_accuracy: 0.2228 - val_loss: 2.3729
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.6385
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1356 - loss: 2.6912  
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1476 - loss: 2.6950
[1m  73/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1528 - loss: 2.6919
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1562 - loss: 2.6900
[1m 126/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1590 - loss: 2.6863
[1m 151/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1604 - loss: 2.6832
[1m 178/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1607 - loss: 2.6816
[1m 206/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1612 - loss: 2.6796
[1m 232/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1617 - loss: 2.6778
[1m 260/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1622 - loss: 2.6756
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1626 - loss: 2.6735
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1631 - loss: 2.6712
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1637 - loss: 2.6692
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1642 - loss: 2.6673
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1648 - loss: 2.6653
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1655 - loss: 2.6633
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1661 - loss: 2.6615
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1666 - loss: 2.6601
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1671 - loss: 2.6588
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1675 - loss: 2.6576
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1679 - loss: 2.6563
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1683 - loss: 2.6548
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1688 - loss: 2.6533
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1693 - loss: 2.6519
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1697 - loss: 2.6504
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1701 - loss: 2.6490
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1706 - loss: 2.6475
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1710 - loss: 2.6459
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1714 - loss: 2.6445
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1717 - loss: 2.6430
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1721 - loss: 2.6416
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1725 - loss: 2.6400
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1728 - loss: 2.6387
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1731 - loss: 2.6373
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1735 - loss: 2.6359
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1738 - loss: 2.6346
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1741 - loss: 2.6333
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1745 - loss: 2.6321
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1748 - loss: 2.6308
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1751 - loss: 2.6295
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1754 - loss: 2.6283
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1757 - loss: 2.6271
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1760 - loss: 2.6260
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1761 - loss: 2.6255 - val_accuracy: 0.2855 - val_loss: 2.2760
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.4841
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2065 - loss: 2.4413  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4559
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2175 - loss: 2.4662
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2161 - loss: 2.4731
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2158 - loss: 2.4721
[1m 153/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2157 - loss: 2.4716
[1m 181/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2161 - loss: 2.4707
[1m 207/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4697
[1m 234/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4697
[1m 258/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4700
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4706
[1m 312/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2168 - loss: 2.4712
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2168 - loss: 2.4715
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2167 - loss: 2.4716
[1m 393/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4719
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2161 - loss: 2.4723
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2159 - loss: 2.4725
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2156 - loss: 2.4726
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2154 - loss: 2.4728
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2151 - loss: 2.4732
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.4736
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2143 - loss: 2.4741
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2140 - loss: 2.4746
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2136 - loss: 2.4749
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2133 - loss: 2.4752
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4754
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2127 - loss: 2.4756
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2124 - loss: 2.4758
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2122 - loss: 2.4758
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2120 - loss: 2.4757
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2118 - loss: 2.4755
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2117 - loss: 2.4753
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2116 - loss: 2.4751
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2115 - loss: 2.4749
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2114 - loss: 2.4746
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2113 - loss: 2.4743
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.4740
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2111 - loss: 2.4736
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2111 - loss: 2.4733
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.4729
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.4725
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.4721
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2110 - loss: 2.4717 - val_accuracy: 0.2748 - val_loss: 2.2029
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.5715
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3489  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2467 - loss: 2.3431
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2444 - loss: 2.3435
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2434 - loss: 2.3445
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3443
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.3476
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2387 - loss: 2.3514
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2374 - loss: 2.3541
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2365 - loss: 2.3562
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3588
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3613
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3637
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2327 - loss: 2.3657
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3676
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2312 - loss: 2.3688
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2306 - loss: 2.3698
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2302 - loss: 2.3707
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2298 - loss: 2.3713
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3719
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2293 - loss: 2.3724
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2291 - loss: 2.3729
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3733
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3739
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2284 - loss: 2.3745
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2282 - loss: 2.3751
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3756
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2278 - loss: 2.3760
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2277 - loss: 2.3764
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2275 - loss: 2.3768
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2274 - loss: 2.3772
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2272 - loss: 2.3775
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3777
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2269 - loss: 2.3780
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2268 - loss: 2.3781
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2267 - loss: 2.3782
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2266 - loss: 2.3782
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2266 - loss: 2.3783
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2265 - loss: 2.3783
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2265 - loss: 2.3783
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2265 - loss: 2.3783
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2264 - loss: 2.3783
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2264 - loss: 2.3783
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2264 - loss: 2.3783 - val_accuracy: 0.3008 - val_loss: 2.1827
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0371
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2615 - loss: 2.3186  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2447 - loss: 2.3515
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2445 - loss: 2.3462
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2443 - loss: 2.3413
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2442 - loss: 2.3379
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2434 - loss: 2.3370
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3364
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2426 - loss: 2.3352
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.3338
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.3335
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3339
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3342
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2430 - loss: 2.3342
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3342
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3339
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3337
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3335
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3335
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3333
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3330
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3329
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3328
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3327
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.3326
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.3325
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.3323
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.3321
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3317
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3314
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3311
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3308
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3305
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3304
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3301
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.3299
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.3295
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.3292
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.3289
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2437 - loss: 2.3286
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2437 - loss: 2.3283
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2438 - loss: 2.3280
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2438 - loss: 2.3277
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2439 - loss: 2.3274
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2439 - loss: 2.3274 - val_accuracy: 0.3127 - val_loss: 2.1569
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.7939
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2912 - loss: 2.1351  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1766
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2024
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2689 - loss: 2.2193
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2667 - loss: 2.2319
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2648 - loss: 2.2412
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2473
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.2501
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2530
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2626 - loss: 2.2553
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.2575
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2593
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2612
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2612 - loss: 2.2630
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2646
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2658
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2670
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2680
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2691
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2700
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2709
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2715
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2721
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2586 - loss: 2.2728
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2734
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2738
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2741
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2743
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2746
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2580 - loss: 2.2748
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2580 - loss: 2.2750
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2580 - loss: 2.2751
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2753
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2754
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2754
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2755
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2756
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2576 - loss: 2.2757
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2758
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2758
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2758
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2758
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2758 - val_accuracy: 0.3071 - val_loss: 2.1083
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4691
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2737  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2525
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2621
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2629
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2606
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2580
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2554
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2625 - loss: 2.2535
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2521
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2514
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 2.2514
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2516
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2518
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2520
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2521
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 2.2525
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 2.2526
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 2.2526
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2527
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.2529
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2632 - loss: 2.2531
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2532
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2534
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2533
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2532
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2531
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2529
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2527
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2525
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2523
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2522
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2520
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2518
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2516
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2515
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2514
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2513
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2511
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2510
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2509
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2508
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2507
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2506 - val_accuracy: 0.3151 - val_loss: 2.1104
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3086
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1940  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1913
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1816
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1766
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1726
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1710
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1714
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1731
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1751
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1770
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1787
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1806
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1817
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1828
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1840
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1853
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1864
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1874
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1883
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1891
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1899
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2775 - loss: 2.1908
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1916
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1922
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2763 - loss: 2.1929
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2760 - loss: 2.1935
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2757 - loss: 2.1941
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2754 - loss: 2.1946
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2751 - loss: 2.1951
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2749 - loss: 2.1955
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2747 - loss: 2.1960
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2746 - loss: 2.1964
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2745 - loss: 2.1968
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2743 - loss: 2.1971
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2742 - loss: 2.1975
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1978
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.1981
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2739 - loss: 2.1983
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2739 - loss: 2.1985
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2738 - loss: 2.1987
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2738 - loss: 2.1989
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.1991
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.1993
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2737 - loss: 2.1993 - val_accuracy: 0.3121 - val_loss: 2.0953
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.9587
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1224  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1346
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1407
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2786 - loss: 2.1564
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1684
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2748 - loss: 2.1751
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2743 - loss: 2.1790
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2743 - loss: 2.1813
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2742 - loss: 2.1838
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2738 - loss: 2.1867
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2733 - loss: 2.1890
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 2.1910
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2722 - loss: 2.1927
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2717 - loss: 2.1940
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.1949
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2711 - loss: 2.1958
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1964
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1969
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1972
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1974
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1977
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1978
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1979
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1978
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1977
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1976
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1976
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1975
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2704 - loss: 2.1973
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1972
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1971
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1969
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.1968
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1965
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.1962
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.1960
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2712 - loss: 2.1957
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.1954
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 2.1951
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2716 - loss: 2.1948
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.1945
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.1942
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.1940
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2720 - loss: 2.1940 - val_accuracy: 0.3351 - val_loss: 2.0781
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.3202
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2675 - loss: 2.2023  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2747 - loss: 2.1784
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1702
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1649
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1621
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1616
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1628
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1640
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1640
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1638
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1637
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1637
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1637
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1632
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1627
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1622
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1617
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1611
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1608
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1604
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1602
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1598
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1593
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1590
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1587
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1585
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1582
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1581
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1580
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1578
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1576
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1574
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1572
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1571
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1570
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1569
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1569
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1568
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1567
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1567
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1566
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1566
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1565 - val_accuracy: 0.3250 - val_loss: 2.1075
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5625 - loss: 1.3548
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3435 - loss: 1.9625  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0282
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0608
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0754
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0825
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0881
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.0938
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 2.0979
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2988 - loss: 2.1009
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1035
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1056
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1074
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1090
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2976 - loss: 2.1108
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 2.1125
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1141
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2966 - loss: 2.1154
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2964 - loss: 2.1164
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 2.1174
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1180
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.1187
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1192
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1196
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1198
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1199
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1202
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1204
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2957 - loss: 2.1206
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1208
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 2.1211
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 2.1213
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1215
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1216
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1217
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1218
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1219
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1219
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1219
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1219
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1219
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1219
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1220
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1220 - val_accuracy: 0.3361 - val_loss: 2.0904
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.8487
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3441 - loss: 2.0293  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0804
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0996
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.1076
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3018 - loss: 2.1102
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1124
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 2.1150
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 2.1153
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2957 - loss: 2.1149
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1151
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1152
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1156
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1160
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2929 - loss: 2.1162
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1166
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1171
[1m 476/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1175
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1177
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1180
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1182
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1185
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1186
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1187
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1188
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1190
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1191
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1191
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1191
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1190
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1189
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1188
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1187
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1186
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1184
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1183
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1182
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1180
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1179
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1177
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1176
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1175
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1174 - val_accuracy: 0.3423 - val_loss: 2.0827
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.1074
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3434 - loss: 2.0418  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0515
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0532
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0539
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3162 - loss: 2.0542
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0554
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0573
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0605
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0639
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0669
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0690
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0703
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0717
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0730
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0741
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0752
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0762
[1m 482/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0771
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0780
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0786
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3088 - loss: 2.0794
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0800
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 2.0805
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3082 - loss: 2.0810
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0816
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3079 - loss: 2.0821
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0826
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3076 - loss: 2.0830
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3074 - loss: 2.0834
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3073 - loss: 2.0837
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0840
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0842
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0843
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0845
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0847
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3067 - loss: 2.0848
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3067 - loss: 2.0849
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0850
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0851
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0852
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0852
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0852
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0853 - val_accuracy: 0.3425 - val_loss: 2.0794
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2500 - loss: 2.4990
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3028 - loss: 2.1394  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2988 - loss: 2.1219
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2991 - loss: 2.1140
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1100
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 2.1097
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3023 - loss: 2.1068
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 2.1059
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.1051
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 2.1036
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 2.1020
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 2.1003
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0985
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0971
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0958
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0946
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0933
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0921
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3078 - loss: 2.0912
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3079 - loss: 2.0908
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0905
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 2.0901
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3083 - loss: 2.0898
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0896
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3086 - loss: 2.0894
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0892
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0890
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3088 - loss: 2.0888
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0885
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0881
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0877
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0873
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0869
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0864
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0860
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0855
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0851
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0847
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0843
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0839
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0835
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0831
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0827
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0824
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0822 - val_accuracy: 0.3452 - val_loss: 2.0703
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.7290
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.3120 - loss: 2.0768  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0987
[1m  74/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3015 - loss: 2.0887
[1m  99/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0822
[1m 126/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3038 - loss: 2.0786
[1m 152/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0773
[1m 178/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0760
[1m 206/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0740
[1m 232/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0726
[1m 259/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0716
[1m 284/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0710
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0701
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 2.0691
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0684
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 2.0677
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3086 - loss: 2.0672
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0668
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0664
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0662
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0660
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0659
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0658
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0658
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0658
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0657
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0658
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0660
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0662
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0663
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0663
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0663
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0663
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0661
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0660
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0658
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0656
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0654
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0653
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0651
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0650
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0648
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0647
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0645
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0645 - val_accuracy: 0.3300 - val_loss: 2.0898
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.8855
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1613  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1195
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1074
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2978 - loss: 2.0971
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0886
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0840
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0794
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0770
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0753
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0737
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0721
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0709
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0696
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3083 - loss: 2.0689
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0680
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0670
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3100 - loss: 2.0660
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0652
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0643
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0636
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0627
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0616
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0608
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0600
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0592
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0585
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0578
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0571
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0564
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0559
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0554
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0549
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3156 - loss: 2.0544
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3158 - loss: 2.0539
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3160 - loss: 2.0535
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3162 - loss: 2.0530
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3165 - loss: 2.0526
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0522
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0517
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0512
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0508
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0505
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0503 - val_accuracy: 0.3397 - val_loss: 2.0687
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0328
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0534  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3376 - loss: 2.0291
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3398 - loss: 2.0230
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3372 - loss: 2.0286
[1m 127/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3360 - loss: 2.0287
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3356 - loss: 2.0274
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3354 - loss: 2.0258
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3354 - loss: 2.0239
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 2.0225
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3356 - loss: 2.0213
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3356 - loss: 2.0202
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 2.0196
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3353 - loss: 2.0193
[1m 366/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3351 - loss: 2.0189
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3348 - loss: 2.0190
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3344 - loss: 2.0192
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 2.0193
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3340 - loss: 2.0193
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 2.0197
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3334 - loss: 2.0201
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 2.0204
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 2.0206
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 2.0208
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3325 - loss: 2.0210
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3323 - loss: 2.0212
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3321 - loss: 2.0214
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3319 - loss: 2.0216
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3317 - loss: 2.0217
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0218
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3314 - loss: 2.0219
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3313 - loss: 2.0219
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3312 - loss: 2.0221
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0222
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 2.0223
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3309 - loss: 2.0224
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0224
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0225
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0226
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 2.0227
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0227
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0227
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3302 - loss: 2.0228
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3302 - loss: 2.0228
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3302 - loss: 2.0228 - val_accuracy: 0.3488 - val_loss: 2.0739
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9586
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2844 - loss: 2.0262  
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2912 - loss: 2.0539
[1m  73/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2952 - loss: 2.0625
[1m  99/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2990 - loss: 2.0618
[1m 127/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0571
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0520
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0476
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0445
[1m 233/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0426
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0409
[1m 288/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0391
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3163 - loss: 2.0370
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0350
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0333
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0321
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0310
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0300
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0290
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0280
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0270
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0261
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0251
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3238 - loss: 2.0245
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0240
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0236
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0234
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0231
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0227
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0223
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0218
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0215
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0213
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0210
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0207
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0205
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0202
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0199
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0195
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0192
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3279 - loss: 2.0188
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3281 - loss: 2.0184
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3283 - loss: 2.0180
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3285 - loss: 2.0177
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3286 - loss: 2.0175 - val_accuracy: 0.3355 - val_loss: 2.0945
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8878
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3110 - loss: 1.9733  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3076 - loss: 2.0007
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3136 - loss: 1.9980
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3188 - loss: 1.9947
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3221 - loss: 1.9925
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3239 - loss: 1.9920
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 1.9920
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 1.9911
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3279 - loss: 1.9906
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3288 - loss: 1.9903
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3295 - loss: 1.9905
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3298 - loss: 1.9914
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3301 - loss: 1.9921
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3303 - loss: 1.9928
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3303 - loss: 1.9934
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 1.9938
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 1.9941
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3308 - loss: 1.9943
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3310 - loss: 1.9946
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 1.9946
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3314 - loss: 1.9944
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 1.9942
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 1.9940
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3321 - loss: 1.9939
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3324 - loss: 1.9937
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3327 - loss: 1.9935
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3329 - loss: 1.9932
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3331 - loss: 1.9930
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3334 - loss: 1.9928
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9926
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3338 - loss: 1.9923
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3340 - loss: 1.9922
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3341 - loss: 1.9920
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3343 - loss: 1.9918
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3344 - loss: 1.9917
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3345 - loss: 1.9916
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3346 - loss: 1.9915
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3347 - loss: 1.9915
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3348 - loss: 1.9914
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3349 - loss: 1.9913
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3350 - loss: 1.9913
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3351 - loss: 1.9912
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3351 - loss: 1.9912
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3352 - loss: 1.9912 - val_accuracy: 0.3317 - val_loss: 2.0952
Epoch 20/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.3232
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1733  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0960
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0622
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 2.0389
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3375 - loss: 2.0289
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3419 - loss: 2.0169
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3443 - loss: 2.0088
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3459 - loss: 2.0023
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3477 - loss: 1.9962
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.9908
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3499 - loss: 1.9867
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3506 - loss: 1.9833
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3513 - loss: 1.9804
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3517 - loss: 1.9784
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3522 - loss: 1.9765
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3526 - loss: 1.9750
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3528 - loss: 1.9739
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3530 - loss: 1.9729
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3534 - loss: 1.9719
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3537 - loss: 1.9709
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3540 - loss: 1.9700
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3542 - loss: 1.9691
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.9683
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.9677
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.9672
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.9668
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.9665
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.9661
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.9657
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.9652
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.9649
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.9646
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.9643
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.9641
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.9639
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.9636
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.9634
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3546 - loss: 1.9633
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3545 - loss: 1.9632
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.9632
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.9632
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3543 - loss: 1.9632
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3542 - loss: 1.9633
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3541 - loss: 1.9634 - val_accuracy: 0.3161 - val_loss: 2.1202
Epoch 21/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9983
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3201 - loss: 1.9331  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3298 - loss: 1.9290
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3307 - loss: 1.9355
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3291 - loss: 1.9459
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 1.9508
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 1.9518
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3324 - loss: 1.9532
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 1.9545
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 1.9558
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9567
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 1.9570
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3348 - loss: 1.9574
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3353 - loss: 1.9581
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3356 - loss: 1.9588
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3362 - loss: 1.9591
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.9592
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3371 - loss: 1.9595
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3375 - loss: 1.9597
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9599
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3382 - loss: 1.9602
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3384 - loss: 1.9606
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.9610
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.9614
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.9616
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9617
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.9619
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 1.9621
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 1.9622
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 1.9624
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 1.9626
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 1.9627
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3400 - loss: 1.9628
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3401 - loss: 1.9629
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 1.9630
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 1.9630
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 1.9629
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3406 - loss: 1.9629
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3407 - loss: 1.9629
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3408 - loss: 1.9628
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 1.9628
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3411 - loss: 1.9628
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3412 - loss: 1.9628
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3413 - loss: 1.9629 - val_accuracy: 0.3409 - val_loss: 2.0932

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 645ms/step
[1m58/86[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 885us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:06[0m 844ms/step
[1m 50/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m102/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 995us/step
[1m158/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 966us/step
[1m216/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 941us/step
[1m269/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 941us/step
[1m328/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 925us/step
[1m382/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 926us/step
[1m437/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 924us/step
[1m490/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 928us/step
[1m546/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 925us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 53/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 970us/step
[1m104/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 977us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 32.78 [%]
Global F1 score (validation) = 31.64 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.01738677 0.01298516 0.01537689 ... 0.03365934 0.03953409 0.01803483]
 [0.00468943 0.00282206 0.0033053  ... 0.09416818 0.0080675  0.00922168]
 [0.00287521 0.00307447 0.00592927 ... 0.0066081  0.00310108 0.00138108]
 ...
 [0.12603542 0.05971568 0.21168797 ... 0.00607364 0.17540318 0.1483929 ]
 [0.20042826 0.03486175 0.10918307 ... 0.02055043 0.10353573 0.073589  ]
 [0.10781756 0.06387761 0.2542409  ... 0.0023598  0.19513759 0.08908091]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 38.74 [%]
Global accuracy score (test) = 29.81 [%]
Global F1 score (train) = 37.95 [%]
Global F1 score (test) = 29.75 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.21      0.38      0.27       184
 CAMINAR CON MÓVIL O LIBRO       0.19      0.20      0.19       184
       CAMINAR USUAL SPEED       0.28      0.40      0.33       184
            CAMINAR ZIGZAG       0.24      0.10      0.14       184
          DE PIE BARRIENDO       0.37      0.41      0.39       184
   DE PIE DOBLANDO TOALLAS       0.44      0.32      0.37       184
    DE PIE MOVIENDO LIBROS       0.29      0.11      0.16       184
          DE PIE USANDO PC       0.11      0.15      0.13       184
        FASE REPOSO CON K5       0.49      0.54      0.51       184
INCREMENTAL CICLOERGOMETRO       0.60      0.35      0.44       184
           SENTADO LEYENDO       0.35      0.28      0.31       184
         SENTADO USANDO PC       0.26      0.20      0.23       184
      SENTADO VIENDO LA TV       0.20      0.28      0.23       184
   SUBIR Y BAJAR ESCALERAS       0.27      0.23      0.25       184
                    TROTAR       0.46      0.54      0.50       161

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


Accuracy capturado en la ejecución 14: 29.81 [%]
F1-score capturado en la ejecución 14: 29.75 [%]

=== EJECUCIÓN 15 ===

--- TRAIN (ejecución 15) ---

--- TEST (ejecución 15) ---
2025-11-07 13:14:35.823635: 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`.
2025-11-07 13:14:35.834871: 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 00:00:1762517675.847966 2795467 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517675.852089 2795467 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517675.861831 2795467 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517675.861848 2795467 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517675.861850 2795467 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517675.861852 2795467 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:14:35.864984: 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 00:00:1762517678.134832 2795467 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517681.205889 2795595 service.cc:152] XLA service 0x73f60801f950 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517681.205949 2795595 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:14:41.271713: 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 00:00:1762517681.694751 2795595 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517684.193735 2795595 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42:59[0m 5s/step - accuracy: 0.0625 - loss: 3.3126
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0775 - loss: 3.3314    
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0754 - loss: 3.3629
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0777 - loss: 3.3652
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0805 - loss: 3.3576
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0831 - loss: 3.3483
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0855 - loss: 3.3376
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0875 - loss: 3.3262
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0890 - loss: 3.3158
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0905 - loss: 3.3052
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0920 - loss: 3.2945
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0933 - loss: 3.2858
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0946 - loss: 3.2763
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0958 - loss: 3.2674
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0969 - loss: 3.2584
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0979 - loss: 3.2498
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0991 - loss: 3.2409
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1002 - loss: 3.2329
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1012 - loss: 3.2252
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1023 - loss: 3.2171
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1034 - loss: 3.2089
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1043 - loss: 3.2019
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1053 - loss: 3.1945
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1061 - loss: 3.1886
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1069 - loss: 3.1824
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1077 - loss: 3.1760
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1086 - loss: 3.1693
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1094 - loss: 3.1632
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1102 - loss: 3.1577
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1111 - loss: 3.1519
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1119 - loss: 3.1465
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1127 - loss: 3.1414
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1135 - loss: 3.1360
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1143 - loss: 3.1309
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1151 - loss: 3.1254
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1158 - loss: 3.1206
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1165 - loss: 3.1161
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1171 - loss: 3.1116
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1178 - loss: 3.1068
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1185 - loss: 3.1025
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1191 - loss: 3.0980
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1197 - loss: 3.0943
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1202 - loss: 3.0905
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1202 - loss: 3.0903 - val_accuracy: 0.2361 - val_loss: 2.3524
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 3.0436
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1540 - loss: 2.7704  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1615 - loss: 2.7679
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1659 - loss: 2.7619
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1670 - loss: 2.7581
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1671 - loss: 2.7578
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1676 - loss: 2.7546
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1677 - loss: 2.7524
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1680 - loss: 2.7477
[1m 233/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1684 - loss: 2.7432
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1690 - loss: 2.7385
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1695 - loss: 2.7343
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1699 - loss: 2.7307
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1703 - loss: 2.7270
[1m 366/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1708 - loss: 2.7234
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1713 - loss: 2.7197
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1717 - loss: 2.7168
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1722 - loss: 2.7136
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1725 - loss: 2.7113
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1728 - loss: 2.7088
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1731 - loss: 2.7070
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.7050
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1737 - loss: 2.7031
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1739 - loss: 2.7014
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1742 - loss: 2.6994
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1744 - loss: 2.6976
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1747 - loss: 2.6960
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1749 - loss: 2.6943
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1752 - loss: 2.6925
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1755 - loss: 2.6910
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1757 - loss: 2.6895
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1759 - loss: 2.6878
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1761 - loss: 2.6864
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1763 - loss: 2.6850
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1765 - loss: 2.6835
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1766 - loss: 2.6821
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1768 - loss: 2.6808
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1770 - loss: 2.6793
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1772 - loss: 2.6778
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1773 - loss: 2.6767
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1775 - loss: 2.6752
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1777 - loss: 2.6739
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1778 - loss: 2.6726
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6714
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6705 - val_accuracy: 0.2783 - val_loss: 2.2881
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.7688
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1743 - loss: 2.5587  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1842 - loss: 2.5247
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1886 - loss: 2.5159
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1919 - loss: 2.5131
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1924 - loss: 2.5125
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1926 - loss: 2.5119
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1929 - loss: 2.5116
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1933 - loss: 2.5125
[1m 255/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1937 - loss: 2.5136
[1m 284/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1941 - loss: 2.5145
[1m 310/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1944 - loss: 2.5152
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1947 - loss: 2.5155
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1949 - loss: 2.5157
[1m 393/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1952 - loss: 2.5156
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1954 - loss: 2.5156
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1957 - loss: 2.5155
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1958 - loss: 2.5153
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1961 - loss: 2.5150
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1963 - loss: 2.5146
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1965 - loss: 2.5144
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1966 - loss: 2.5141
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1968 - loss: 2.5139
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1970 - loss: 2.5136
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1972 - loss: 2.5134
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1973 - loss: 2.5131
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1975 - loss: 2.5129
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1976 - loss: 2.5126
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1978 - loss: 2.5123
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1979 - loss: 2.5121
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1980 - loss: 2.5118
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1981 - loss: 2.5116
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1982 - loss: 2.5112
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.5109
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1985 - loss: 2.5105
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1986 - loss: 2.5100
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1988 - loss: 2.5094
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1990 - loss: 2.5090
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1992 - loss: 2.5085
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1993 - loss: 2.5080
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1995 - loss: 2.5074
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1997 - loss: 2.5069
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1998 - loss: 2.5067 - val_accuracy: 0.2789 - val_loss: 2.2325
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 3.3066
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1981 - loss: 2.4916  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2089 - loss: 2.4517
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2119 - loss: 2.4492
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2136 - loss: 2.4409
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2143 - loss: 2.4350
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.4308
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2156 - loss: 2.4272
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4245
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2168 - loss: 2.4233
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2170 - loss: 2.4223
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2174 - loss: 2.4211
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2174 - loss: 2.4204
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2175 - loss: 2.4198
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2175 - loss: 2.4192
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2175 - loss: 2.4187
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4183
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4179
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4176
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4174
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4170
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2181 - loss: 2.4168
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4166
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4162
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4160
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4158
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4156
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4155
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4154
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4153
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4152
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4151
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4149
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4149
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4148
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4148
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4147
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4146
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4145
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4144
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4143
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4142
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4142
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4141
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4141 - val_accuracy: 0.2785 - val_loss: 2.2218
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.8785
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2628 - loss: 2.3464  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2526 - loss: 2.3451
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2470 - loss: 2.3369
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2450 - loss: 2.3298
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2437 - loss: 2.3270
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.3261
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2418 - loss: 2.3268
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2410 - loss: 2.3287
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2402 - loss: 2.3309
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2394 - loss: 2.3332
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2383 - loss: 2.3355
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2376 - loss: 2.3373
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2372 - loss: 2.3386
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2369 - loss: 2.3399
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2365 - loss: 2.3411
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2362 - loss: 2.3422
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2358 - loss: 2.3431
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3439
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2352 - loss: 2.3445
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3450
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3456
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3462
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3468
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3474
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3480
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3486
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3491
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3495
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2328 - loss: 2.3498
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2326 - loss: 2.3500
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3501
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3504
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3505
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3507
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3508
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3509
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3509
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2316 - loss: 2.3510
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3510
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2314 - loss: 2.3510
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2314 - loss: 2.3510
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2313 - loss: 2.3511
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2313 - loss: 2.3511 - val_accuracy: 0.2855 - val_loss: 2.1843
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4680
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2331 - loss: 2.2913  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2334 - loss: 2.2910
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2337 - loss: 2.2923
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2347 - loss: 2.2919
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2355 - loss: 2.2938
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2359 - loss: 2.2957
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.2976
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.2995
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2366 - loss: 2.3008
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2369 - loss: 2.3015
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2373 - loss: 2.3017
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2376 - loss: 2.3016
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3015
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3016
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3015
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2380 - loss: 2.3011
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3008
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2380 - loss: 2.3004
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2381 - loss: 2.3000
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.2996
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.2994
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2383 - loss: 2.2992
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2384 - loss: 2.2992
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2385 - loss: 2.2991
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2386 - loss: 2.2990
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2388 - loss: 2.2989
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2389 - loss: 2.2988
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2390 - loss: 2.2989
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2391 - loss: 2.2989
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2392 - loss: 2.2990
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2393 - loss: 2.2991
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2394 - loss: 2.2992
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2395 - loss: 2.2993
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2395 - loss: 2.2994
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2396 - loss: 2.2995
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2396 - loss: 2.2996
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2396 - loss: 2.2997
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2397 - loss: 2.2997
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2398 - loss: 2.2997
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2398 - loss: 2.2997
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2399 - loss: 2.2996
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2400 - loss: 2.2995 - val_accuracy: 0.2883 - val_loss: 2.1964
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2506
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2748 - loss: 2.2226  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2705 - loss: 2.2314
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2713 - loss: 2.2315
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2695 - loss: 2.2357
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.2383
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2659 - loss: 2.2417
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2646 - loss: 2.2450
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2480
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2622 - loss: 2.2509
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2612 - loss: 2.2535
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2552
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2572
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2592
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2609
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2586 - loss: 2.2623
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2635
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2645
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2653
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.2662
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2670
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2566 - loss: 2.2676
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2680
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2682
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2684
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2685
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2686
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2686
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2687
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2688
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2688
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2690
[1m 873/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2691
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2691
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2692
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2692
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2692
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2692
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2691
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2690
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2689
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2687
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2686
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2685 - val_accuracy: 0.3095 - val_loss: 2.1367
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m35s[0m 30ms/step - accuracy: 0.1875 - loss: 2.3402
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2627 - loss: 2.3016  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2697
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2645 - loss: 2.2556
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2646 - loss: 2.2526
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2645 - loss: 2.2507
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2512
[1m 181/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2519
[1m 207/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.2526
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2617 - loss: 2.2517
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2504
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2612 - loss: 2.2493
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2610 - loss: 2.2487
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2483
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2478
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2473
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2468
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2459
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2450
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2441
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2433
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2428
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2423
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2419
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2417
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2417
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2416
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2416
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2415
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2414
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2412
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2411
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2410
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2408
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2406
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2404
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2402
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2400
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2398
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2396
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2394
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2393
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2392 - val_accuracy: 0.3129 - val_loss: 2.1499
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3125 - loss: 1.8841
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2973 - loss: 2.2220  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2852 - loss: 2.2370
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2785 - loss: 2.2358
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2728 - loss: 2.2352
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2685 - loss: 2.2344
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2323
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2310
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2300
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2622 - loss: 2.2287
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2275
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2266
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2260
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2613 - loss: 2.2258
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2613 - loss: 2.2255
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2251
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2248
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2244
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2239
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2236
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2233
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2620 - loss: 2.2229
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.2225
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2623 - loss: 2.2221
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2624 - loss: 2.2216
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2625 - loss: 2.2213
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2625 - loss: 2.2211
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2626 - loss: 2.2210
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2208
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2207
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2206
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2205
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2205
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2205
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2205
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2205
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2204
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2204
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2203
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2203
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2203
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2204
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2204
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2204 - val_accuracy: 0.3347 - val_loss: 2.1193
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0772
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3346 - loss: 2.0449  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1040
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1332
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1433
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1489
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1525
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1546
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1558
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1569
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1577
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1582
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1590
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1596
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1606
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1618
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1631
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1639
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1647
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1653
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1659
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2792 - loss: 2.1665
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1669
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1672
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1676
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1679
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1681
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1682
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1684
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1684
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1685
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1686
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1686
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1686
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1686
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1686
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1687
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1687
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2786 - loss: 2.1688
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1689
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1690
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1691
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1693
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1693 - val_accuracy: 0.3448 - val_loss: 2.1040
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2587
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1809  
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1755
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1811
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1840
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1839
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1846
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1861
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 2.1869
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2753 - loss: 2.1873
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2754 - loss: 2.1871
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 2.1866
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2757 - loss: 2.1860
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1852
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2759 - loss: 2.1846
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2759 - loss: 2.1841
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2760 - loss: 2.1834
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2762 - loss: 2.1825
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1818
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1815
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1811
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1808
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1807
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1806
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1804
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1801
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1797
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1794
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1790
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1786
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1782
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1777
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1772
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1768
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1763
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1758
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2775 - loss: 2.1754
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1750
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2777 - loss: 2.1745
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2777 - loss: 2.1742
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1738
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1733
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1730
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1728 - val_accuracy: 0.3365 - val_loss: 2.1223
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3637
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2662 - loss: 2.1901  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2729 - loss: 2.1734
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2745 - loss: 2.1740
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2737 - loss: 2.1770
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2745 - loss: 2.1765
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 2.1746
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1743
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1747
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2763 - loss: 2.1750
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1749
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1737
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1721
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1706
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1691
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1680
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1670
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1659
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1652
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1645
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1637
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1629
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1623
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1616
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1610
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1604
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1597
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1591
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1585
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1580
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1575
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1569
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1564
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1560
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1555
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1552
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1548
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1545
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1542
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1538
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1534
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1530
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1527
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1526 - val_accuracy: 0.3405 - val_loss: 2.1220
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.8817
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3344 - loss: 1.9550  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3203 - loss: 1.9985
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0199
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0322
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0420
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.0491
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 2.0562
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2983 - loss: 2.0616
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 2.0671
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2957 - loss: 2.0721
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.0770
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 2.0808
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.0841
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2918 - loss: 2.0866
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2911 - loss: 2.0890
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2907 - loss: 2.0908
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2902 - loss: 2.0925
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2899 - loss: 2.0939
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2895 - loss: 2.0955
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.0970
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.0983
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.0993
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2887 - loss: 2.1002
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1012
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1020
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1028
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1035
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1043
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2880 - loss: 2.1051
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1057
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1062
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1067
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1071
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1075
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1080
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1085
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1090
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1094
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1098
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1101
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1104
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1107
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1109 - val_accuracy: 0.3464 - val_loss: 2.0942
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.8069
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1002  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2915 - loss: 2.1031
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1076
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1062
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 2.1048
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1056
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1065
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1069
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1062
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1052
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1044
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1038
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1030
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1020
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1014
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1008
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1003
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.0998
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 2.0996
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2948 - loss: 2.0993
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2950 - loss: 2.0991
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2952 - loss: 2.0990
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 2.0989
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 2.0989
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2958 - loss: 2.0989
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0989
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0991
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2961 - loss: 2.0992
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2962 - loss: 2.0993
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2963 - loss: 2.0994
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 2.0994
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 2.0995
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2965 - loss: 2.0996
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2966 - loss: 2.0998
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2966 - loss: 2.0999
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1002
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1004
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1006
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1008
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1010
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 2.1012
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 2.1013
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2968 - loss: 2.1014 - val_accuracy: 0.3095 - val_loss: 2.1125
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.1690
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3157 - loss: 2.1201  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3057 - loss: 2.1174
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3048 - loss: 2.1098
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 2.1022
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 2.1008
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 2.1001
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0993
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0986
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 2.0978
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0971
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0967
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0961
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0952
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0943
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0931
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0921
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0912
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0904
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 2.0895
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0887
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.0877
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0871
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0866
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0861
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0856
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0852
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0848
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0845
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0844
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0842
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0840
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0838
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0836
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0834
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0832
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0830
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0829
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0828
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0827
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0825
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0825
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0824
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0824 - val_accuracy: 0.3500 - val_loss: 2.1077
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 2.1707
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3794 - loss: 1.9960  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3615 - loss: 2.0196
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3526 - loss: 2.0338
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3468 - loss: 2.0400
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 2.0458
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 2.0515
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 2.0556
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3350 - loss: 2.0578
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 2.0590
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3324 - loss: 2.0593
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0592
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3300 - loss: 2.0592
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3293 - loss: 2.0590
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 2.0591
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3279 - loss: 2.0589
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0590
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0591
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0592
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0593
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0593
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0595
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0599
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0603
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0607
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0612
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0617
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0621
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0624
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0627
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0631
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0635
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0639
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3215 - loss: 2.0641
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0644
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0647
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0648
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0650
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0652
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0654
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0657
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0659
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0661 - val_accuracy: 0.3218 - val_loss: 2.1138
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.5835
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0101  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0413
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0576
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0643
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0692
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0708
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0712
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 2.0700
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0690
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0678
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3076 - loss: 2.0665
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0656
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 2.0646
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3088 - loss: 2.0638
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0632
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0628
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0623
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0619
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0617
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0615
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0613
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0613
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0612
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0612
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0612
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0611
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0610
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0608
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0606
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0602
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0599
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0596
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0594
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0592
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0591
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0589
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0587
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0585
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0583
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0581
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0580
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0579 - val_accuracy: 0.3256 - val_loss: 2.0838
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1437
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0535  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0323
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3187 - loss: 2.0353
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3160 - loss: 2.0434
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0488
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0518
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0538
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0553
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0559
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0559
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0558
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0559
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0565
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0571
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0576
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0578
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0578
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0575
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0572
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0569
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0566
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0564
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0561
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0559
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0558
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0557
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0557
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0558
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0558
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0558
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0558
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0558
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0558
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0558
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0558
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0558
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0557
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0556
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0555
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0554
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0552
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0550
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0550 - val_accuracy: 0.3274 - val_loss: 2.1206
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.4375 - loss: 1.7496
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3451 - loss: 2.0086  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3336 - loss: 2.0234
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 2.0221
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3330 - loss: 2.0197
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3323 - loss: 2.0184
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 2.0191
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3302 - loss: 2.0205
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3298 - loss: 2.0212
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3293 - loss: 2.0220
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3289 - loss: 2.0220
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 2.0220
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0221
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0223
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0226
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0230
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0232
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0236
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0239
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0240
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0240
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0240
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0239
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0239
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0239
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 2.0240
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0241
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0242
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0244
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0246
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0248
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0249
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0250
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0251
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0252
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0254
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0255
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0255
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0255
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0255
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0255
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0255
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0255
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0255 - val_accuracy: 0.3383 - val_loss: 2.1152
Epoch 20/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1304
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2683 - loss: 2.1248  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2887 - loss: 2.0942
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 2.0773
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0728
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0681
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0636
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0609
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0585
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0572
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0550
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0527
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0501
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0477
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0454
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0432
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0414
[1m 470/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0400
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 2.0385
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3162 - loss: 2.0373
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 2.0363
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0354
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0346
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0340
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0336
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0331
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0327
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3186 - loss: 2.0323
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 2.0320
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0316
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0312
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0309
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0306
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0303
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0300
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0297
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0295
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0292
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0290
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0288
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0287
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0285
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0283
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0281 - val_accuracy: 0.3365 - val_loss: 2.0949
Epoch 21/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.8832
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3668 - loss: 1.9555  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3602 - loss: 1.9777
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3551 - loss: 1.9914
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3517 - loss: 1.9980
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3487 - loss: 2.0026
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3460 - loss: 2.0055
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3444 - loss: 2.0056
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 2.0049
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3421 - loss: 2.0046
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 2.0038
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3411 - loss: 2.0028
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3410 - loss: 2.0019
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3409 - loss: 2.0007
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3408 - loss: 2.0000
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3406 - loss: 1.9995
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3406 - loss: 1.9990
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3405 - loss: 1.9987
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.9984
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 1.9982
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3399 - loss: 1.9983
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.9985
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.9988
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3394 - loss: 1.9989
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.9991
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.9993
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9996
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9998
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9998
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9998
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.9997
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.9996
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9993
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9991
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.9988
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.9987
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 1.9986
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9986
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.9985
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.9986
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3388 - loss: 1.9987
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 1.9987
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3386 - loss: 1.9986
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3385 - loss: 1.9986
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3385 - loss: 1.9986 - val_accuracy: 0.3304 - val_loss: 2.1049
Epoch 22/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.6510
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3063 - loss: 2.1141  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0591
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3359 - loss: 2.0340
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3383 - loss: 2.0219
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3401 - loss: 2.0128
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3419 - loss: 2.0049
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3426 - loss: 1.9986
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3430 - loss: 1.9933
[1m 258/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3434 - loss: 1.9898
[1m 285/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3435 - loss: 1.9876
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.9852
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3440 - loss: 1.9836
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3440 - loss: 1.9824
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3441 - loss: 1.9810
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3442 - loss: 1.9798
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3442 - loss: 1.9795
[1m 482/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3440 - loss: 1.9797
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3438 - loss: 1.9800
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3437 - loss: 1.9801
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3436 - loss: 1.9801
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3435 - loss: 1.9802
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3434 - loss: 1.9802
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9802
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9802
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9802
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9802
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9800
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9799
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3434 - loss: 1.9797
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3434 - loss: 1.9795
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3434 - loss: 1.9794
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9793
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9791
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9790
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9789
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9787
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9785
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9784
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9782
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9781
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9780
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9779 - val_accuracy: 0.3339 - val_loss: 2.1147

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 649ms/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m7:54[0m 822ms/step
[1m 52/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 995us/step  
[1m109/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 940us/step
[1m166/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 922us/step
[1m220/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 925us/step
[1m277/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 917us/step
[1m336/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 905us/step
[1m392/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 904us/step
[1m445/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 910us/step
[1m503/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 905us/step
[1m560/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 903us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 939us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 51/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m107/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 956us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 34.09 [%]
Global F1 score (validation) = 32.53 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.01729283 0.00805764 0.01674915 ... 0.02086013 0.04194053 0.00979274]
 [0.00210649 0.00109636 0.00110048 ... 0.13115092 0.00724456 0.00404123]
 [0.00047097 0.00031859 0.00069017 ... 0.00587096 0.00133024 0.00094675]
 ...
 [0.11582195 0.0920607  0.14652255 ... 0.00840611 0.123665   0.0883881 ]
 [0.09607463 0.07161622 0.07097252 ... 0.02983206 0.03755983 0.09249068]
 [0.06170995 0.05894002 0.19383165 ... 0.00500455 0.13447407 0.12925915]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 40.69 [%]
Global accuracy score (test) = 28.32 [%]
Global F1 score (train) = 39.67 [%]
Global F1 score (test) = 26.97 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.29      0.34      0.31       184
 CAMINAR CON MÓVIL O LIBRO       0.06      0.02      0.03       184
       CAMINAR USUAL SPEED       0.20      0.10      0.14       184
            CAMINAR ZIGZAG       0.23      0.44      0.30       184
          DE PIE BARRIENDO       0.35      0.23      0.28       184
   DE PIE DOBLANDO TOALLAS       0.39      0.38      0.39       184
    DE PIE MOVIENDO LIBROS       0.35      0.32      0.33       184
          DE PIE USANDO PC       0.09      0.13      0.11       184
        FASE REPOSO CON K5       0.34      0.67      0.45       184
INCREMENTAL CICLOERGOMETRO       0.40      0.45      0.42       184
           SENTADO LEYENDO       0.26      0.24      0.25       184
         SENTADO USANDO PC       0.22      0.04      0.06       184
      SENTADO VIENDO LA TV       0.16      0.21      0.18       184
   SUBIR Y BAJAR ESCALERAS       0.30      0.21      0.24       184
                    TROTAR       0.62      0.50      0.55       161

                  accuracy                           0.28      2737
                 macro avg       0.28      0.28      0.27      2737
              weighted avg       0.28      0.28      0.27      2737


Accuracy capturado en la ejecución 15: 28.32 [%]
F1-score capturado en la ejecución 15: 26.97 [%]

=== EJECUCIÓN 16 ===

--- TRAIN (ejecución 16) ---

--- TEST (ejecución 16) ---
2025-11-07 13:15:57.661075: 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`.
2025-11-07 13:15:57.672582: 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 00:00:1762517757.685754 2799003 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517757.689887 2799003 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517757.699701 2799003 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517757.699728 2799003 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517757.699730 2799003 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517757.699731 2799003 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:15:57.702879: 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 00:00:1762517759.990065 2799003 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517763.015694 2799133 service.cc:152] XLA service 0x7e3154007090 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517763.015725 2799133 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:16:03.081099: 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 00:00:1762517763.523665 2799133 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517766.090700 2799133 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:10[0m 5s/step - accuracy: 0.1875 - loss: 3.3465
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0880 - loss: 3.3333    
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0823 - loss: 3.3496
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0840 - loss: 3.3389
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0853 - loss: 3.3267
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0856 - loss: 3.3182
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0862 - loss: 3.3108
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0867 - loss: 3.3025
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0872 - loss: 3.2930
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0877 - loss: 3.2847
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0884 - loss: 3.2760
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0892 - loss: 3.2677
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0901 - loss: 3.2592
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0911 - loss: 3.2502
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0920 - loss: 3.2414
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0930 - loss: 3.2326
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0939 - loss: 3.2248
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0948 - loss: 3.2163
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0956 - loss: 3.2090
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0962 - loss: 3.2023
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0969 - loss: 3.1955
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0976 - loss: 3.1893
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0982 - loss: 3.1835
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0988 - loss: 3.1779
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0995 - loss: 3.1723
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1001 - loss: 3.1665
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1008 - loss: 3.1613
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1014 - loss: 3.1563
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1020 - loss: 3.1516
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1027 - loss: 3.1465
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1033 - loss: 3.1417
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1040 - loss: 3.1366
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1046 - loss: 3.1320
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1053 - loss: 3.1275
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1060 - loss: 3.1226
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1067 - loss: 3.1178
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1074 - loss: 3.1135
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1081 - loss: 3.1087
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1087 - loss: 3.1044
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1095 - loss: 3.0996
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1101 - loss: 3.0953
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1108 - loss: 3.0909
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1115 - loss: 3.0866
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1118 - loss: 3.0846
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1118 - loss: 3.0844 - val_accuracy: 0.2490 - val_loss: 2.3564
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2632
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1687 - loss: 2.7019  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1586 - loss: 2.7223
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1601 - loss: 2.7100
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1601 - loss: 2.7086
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1608 - loss: 2.7071
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1615 - loss: 2.7056
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1629 - loss: 2.7022
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1643 - loss: 2.6992
[1m 234/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1650 - loss: 2.6976
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1656 - loss: 2.6955
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1658 - loss: 2.6939
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1658 - loss: 2.6929
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1658 - loss: 2.6918
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1659 - loss: 2.6902
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1659 - loss: 2.6890
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1659 - loss: 2.6873
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1662 - loss: 2.6855
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1664 - loss: 2.6834
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1666 - loss: 2.6817
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1667 - loss: 2.6803
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1668 - loss: 2.6787
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1669 - loss: 2.6771
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1670 - loss: 2.6754
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1672 - loss: 2.6738
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1674 - loss: 2.6724
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1675 - loss: 2.6711
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1676 - loss: 2.6698
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1677 - loss: 2.6684
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1679 - loss: 2.6672
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1681 - loss: 2.6659
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1682 - loss: 2.6647
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1684 - loss: 2.6635
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1686 - loss: 2.6622
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1687 - loss: 2.6609
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1689 - loss: 2.6597
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1690 - loss: 2.6586
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1692 - loss: 2.6574
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1694 - loss: 2.6562
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1695 - loss: 2.6550
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1697 - loss: 2.6538
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1699 - loss: 2.6526
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1701 - loss: 2.6516
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.1703 - loss: 2.6505
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1703 - loss: 2.6504 - val_accuracy: 0.2605 - val_loss: 2.2485
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.7144
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1672 - loss: 2.6656  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1688 - loss: 2.6545
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1707 - loss: 2.6363
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1729 - loss: 2.6225
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1749 - loss: 2.6137
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1769 - loss: 2.6065
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1787 - loss: 2.5990
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1804 - loss: 2.5914
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1816 - loss: 2.5852
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1830 - loss: 2.5788
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.5739
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1849 - loss: 2.5690
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.5647
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1864 - loss: 2.5610
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1870 - loss: 2.5572
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1877 - loss: 2.5538
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1883 - loss: 2.5509
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1888 - loss: 2.5484
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1892 - loss: 2.5464
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1897 - loss: 2.5439
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1902 - loss: 2.5419
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1905 - loss: 2.5400
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1908 - loss: 2.5382
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1912 - loss: 2.5365
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1915 - loss: 2.5350
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1918 - loss: 2.5334
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1921 - loss: 2.5322
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1923 - loss: 2.5308
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1925 - loss: 2.5295
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1927 - loss: 2.5282
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1930 - loss: 2.5268
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1932 - loss: 2.5254
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1934 - loss: 2.5241
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1936 - loss: 2.5229
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1938 - loss: 2.5216
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1940 - loss: 2.5205
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1942 - loss: 2.5193
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1944 - loss: 2.5182
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1946 - loss: 2.5173
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1947 - loss: 2.5163
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1949 - loss: 2.5153
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1951 - loss: 2.5143
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1951 - loss: 2.5140 - val_accuracy: 0.2746 - val_loss: 2.2026
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 2.1891
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2174 - loss: 2.3849  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2021 - loss: 2.4274
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1981 - loss: 2.4368
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1990 - loss: 2.4299
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2007 - loss: 2.4261
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.4252
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2037 - loss: 2.4241
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2050 - loss: 2.4229
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2062 - loss: 2.4222
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2072 - loss: 2.4219
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4210
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2091 - loss: 2.4199
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2099 - loss: 2.4190
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2106 - loss: 2.4180
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2111 - loss: 2.4173
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2115 - loss: 2.4168
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2117 - loss: 2.4164
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2120 - loss: 2.4161
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2123 - loss: 2.4157
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2126 - loss: 2.4152
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2128 - loss: 2.4151
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4150
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2132 - loss: 2.4150
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2133 - loss: 2.4149
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2135 - loss: 2.4147
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2136 - loss: 2.4146
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2137 - loss: 2.4144
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2138 - loss: 2.4143
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2140 - loss: 2.4142
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2141 - loss: 2.4141
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2142 - loss: 2.4140
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2143 - loss: 2.4138
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2144 - loss: 2.4135
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2145 - loss: 2.4132
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2147 - loss: 2.4128
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2148 - loss: 2.4125
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2149 - loss: 2.4121
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2151 - loss: 2.4118
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2152 - loss: 2.4116
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2153 - loss: 2.4113
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2154 - loss: 2.4110
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2154 - loss: 2.4107
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2155 - loss: 2.4105 - val_accuracy: 0.2906 - val_loss: 2.1911
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2793
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2305 - loss: 2.3447  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2371 - loss: 2.3374
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2374 - loss: 2.3328
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2385 - loss: 2.3328
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2393 - loss: 2.3330
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2388 - loss: 2.3345
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3366
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2370 - loss: 2.3389
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2365 - loss: 2.3400
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2361 - loss: 2.3406
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.3413
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2358 - loss: 2.3420
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2354 - loss: 2.3428
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3437
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3448
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2339 - loss: 2.3458
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3464
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3467
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3468
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2328 - loss: 2.3470
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2326 - loss: 2.3470
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3470
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2324 - loss: 2.3469
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3470
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3470
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3470
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3470
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3471
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3471
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3471
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3470
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3469
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3468
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3467
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2316 - loss: 2.3467
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2316 - loss: 2.3467
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2316 - loss: 2.3467
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3467
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3468
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3468
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3469
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3469
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2314 - loss: 2.3470
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2314 - loss: 2.3470 - val_accuracy: 0.2932 - val_loss: 2.1638
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.4308
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2677 - loss: 2.2841  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2571 - loss: 2.2837
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2903
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2951
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2483 - loss: 2.2989
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2458 - loss: 2.3027
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2447 - loss: 2.3049
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2441 - loss: 2.3060
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2438 - loss: 2.3064
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2437 - loss: 2.3071
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2435 - loss: 2.3080
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3093
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.3099
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.3098
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3099
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3097
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2424 - loss: 2.3096
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2422 - loss: 2.3096
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2420 - loss: 2.3095
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3092
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3088
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3086
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3085
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3082
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2419 - loss: 2.3080
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2420 - loss: 2.3078
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2420 - loss: 2.3075
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2420 - loss: 2.3073
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2421 - loss: 2.3070
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2421 - loss: 2.3066
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2422 - loss: 2.3063
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2422 - loss: 2.3060
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2423 - loss: 2.3057
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2423 - loss: 2.3054
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2424 - loss: 2.3050
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2424 - loss: 2.3047
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3043
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3040
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3037
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3034
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3031
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3029
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3027 - val_accuracy: 0.3184 - val_loss: 2.1301
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.0284
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2671 - loss: 2.1501  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2680 - loss: 2.1879
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2670 - loss: 2.2012
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2646 - loss: 2.2136
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2632 - loss: 2.2214
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2287
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2334
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2363
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2383
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2405
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2418
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2428
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2437
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2576 - loss: 2.2449
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2459
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.2471
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.2479
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2572 - loss: 2.2486
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.2491
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2570 - loss: 2.2495
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2569 - loss: 2.2502
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2507
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2566 - loss: 2.2513
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2519
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2523
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2527
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2530
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2532
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2533
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2535
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2536
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2537
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2538
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2538
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2538
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2538
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2538
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2539
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2539
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2539
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2540
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2540
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2540 - val_accuracy: 0.3375 - val_loss: 2.1124
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.8445
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2044 - loss: 2.3588  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2204 - loss: 2.3046
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2291 - loss: 2.2855
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2349 - loss: 2.2758
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.2710
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2402 - loss: 2.2671
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2422 - loss: 2.2630
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2445 - loss: 2.2595
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2564
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2531
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.2497
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2464
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2522 - loss: 2.2441
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2422
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2407
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2393
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2381
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2372
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2365
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2565 - loss: 2.2357
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2568 - loss: 2.2350
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.2345
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2339
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2335
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2332
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2329
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2326
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2323
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2319
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2586 - loss: 2.2317
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2314
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2311
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2309
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2307
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2305
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2303
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2302
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2300
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2298
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2296
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2294
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2292
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2291 - val_accuracy: 0.3288 - val_loss: 2.1044
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.7432
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2240 - loss: 2.2945  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2349 - loss: 2.2771
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2443 - loss: 2.2620
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2489
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2393
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2340
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2612 - loss: 2.2292
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2246
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2211
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2651 - loss: 2.2187
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.2169
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2666 - loss: 2.2151
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2673 - loss: 2.2134
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2681 - loss: 2.2111
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2092
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.2074
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2701 - loss: 2.2062
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.2054
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2709 - loss: 2.2048
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2712 - loss: 2.2042
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.2039
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.2037
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.2035
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.2033
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.2030
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2028
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2025
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2023
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2021
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2019
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2017
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2016
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2013
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.2011
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.2009
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2721 - loss: 2.2007
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2721 - loss: 2.2005
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.2003
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.2002
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.2000
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.1998
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.1995
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.1993
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2722 - loss: 2.1993 - val_accuracy: 0.3335 - val_loss: 2.1095
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.5000 - loss: 1.8725
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3535 - loss: 2.0173  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0719
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 2.1040
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3030 - loss: 2.1157
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 2.1222
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1271
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1300
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1322
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1350
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2905 - loss: 2.1381
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1403
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1417
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1430
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1444
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2869 - loss: 2.1460
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1477
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1489
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1500
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1508
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1515
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1520
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1524
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1527
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1530
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1533
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1535
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1537
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1539
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1542
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1544
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1546
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1547
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1550
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1552
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1554
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1556
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1557
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1558
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1559
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1561
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1562
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1564
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1565 - val_accuracy: 0.3403 - val_loss: 2.1007
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3750 - loss: 1.9128
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0523  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0799
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0957
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3025 - loss: 2.1035
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1104
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1128
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1146
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1169
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1204
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1230
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2986 - loss: 2.1255
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1286
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2976 - loss: 2.1308
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1327
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1343
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1356
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2964 - loss: 2.1367
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1376
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1385
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1394
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1402
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1410
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1417
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1424
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1430
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1437
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1443
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1447
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1451
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1455
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1457
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1460
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1462
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1465
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1467
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2916 - loss: 2.1469
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1471
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2912 - loss: 2.1473
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2911 - loss: 2.1474
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2909 - loss: 2.1475
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2908 - loss: 2.1476
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2906 - loss: 2.1476
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2906 - loss: 2.1476 - val_accuracy: 0.3516 - val_loss: 2.0969
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.7569
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0442  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3113 - loss: 2.1026
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3048 - loss: 2.1137
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1217
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 2.1291
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1340
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1377
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1394
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1397
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1397
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1392
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1387
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1380
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1373
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1368
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1363
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 2.1359
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1354
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1351
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1348
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1345
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1341
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1337
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1333
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1330
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1325
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1321
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1317
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1313
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1310
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1308
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1306
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1304
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1302
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1301
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1300
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1297
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1295
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1292
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1290
[1m1103/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1288
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1286
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1284 - val_accuracy: 0.3595 - val_loss: 2.0867
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2277
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3130 - loss: 2.1061  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3062 - loss: 2.1108
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1108
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1066
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1031
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1033
[1m 181/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1053
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1082
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1100
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1113
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1121
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1128
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1135
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1147
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1158
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 2.1166
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2936 - loss: 2.1173
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1177
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1180
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1182
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1185
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1186
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1187
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1188
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1189
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1188
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1186
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1184
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1182
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1179
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1176
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1173
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 2.1171
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1168
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1166
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1163
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1161
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1158
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1157
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1155
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1154
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1153
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1152 - val_accuracy: 0.3532 - val_loss: 2.0630
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2601
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0935  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3107 - loss: 2.1012
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0922
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0899
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0902
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0888
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0884
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0888
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0888
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3079 - loss: 2.0887
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0880
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0873
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 2.0867
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0863
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0863
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0865
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0866
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0867
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0869
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0871
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0873
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0874
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0876
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0877
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0879
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0881
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0882
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0884
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0885
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0886
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0887
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0887
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0887
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0888
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0889
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0889
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0888
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0888
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0888
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3057 - loss: 2.0888
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0888
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0888
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0888 - val_accuracy: 0.3460 - val_loss: 2.0822
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9443
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3099 - loss: 2.1719  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 2.1568
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.1399
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.1290
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.1239
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.1193
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.1148
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 2.1112
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.1082
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 2.1066
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.1046
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 2.1024
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.1007
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0996
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0984
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0975
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0970
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0964
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0960
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0955
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0950
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0945
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0939
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3100 - loss: 2.0935
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0931
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0928
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0924
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0919
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0914
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0909
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0904
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0899
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0894
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0890
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0886
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0882
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0878
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0876
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0873
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0870
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0868
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0865
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0864 - val_accuracy: 0.3351 - val_loss: 2.1048
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0709
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3072 - loss: 2.0228  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0147
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0184
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0226
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0260
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0282
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 2.0298
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0325
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0345
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0362
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0376
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0383
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0389
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0396
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0402
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0405
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0405
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0406
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0408
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0411
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0416
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0420
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0424
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0427
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0431
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0433
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0436
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0437
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0439
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0441
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0443
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0445
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0447
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0450
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0452
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0453
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0455
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0456
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0458
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0460
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0461
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0463
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0465
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0466 - val_accuracy: 0.3423 - val_loss: 2.0921
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.6768
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3644 - loss: 1.9863  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3501 - loss: 2.0164
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3458 - loss: 2.0207
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3410 - loss: 2.0270
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3390 - loss: 2.0264
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3382 - loss: 2.0252
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3370 - loss: 2.0254
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3358 - loss: 2.0257
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3344 - loss: 2.0263
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3330 - loss: 2.0274
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 2.0279
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3312 - loss: 2.0281
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0284
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3300 - loss: 2.0289
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3294 - loss: 2.0294
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 2.0303
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0312
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0320
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0329
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0336
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0341
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3255 - loss: 2.0344
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0347
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0349
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0352
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0353
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0354
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0354
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0354
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 2.0354
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0354
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0354
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0353
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0352
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0351
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0351
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0350
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0350
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0350
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0350
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0351
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0351
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0351 - val_accuracy: 0.3417 - val_loss: 2.0827
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.5000 - loss: 1.6834
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3806 - loss: 1.9462  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3483 - loss: 1.9787
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3411 - loss: 1.9841
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.9894
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3344 - loss: 1.9933
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.9955
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.9979
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0010
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3299 - loss: 2.0041
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3289 - loss: 2.0062
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0080
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0094
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0104
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0106
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0108
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0111
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0115
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0119
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0122
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0123
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0122
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0121
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0121
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0121
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0120
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0118
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0116
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0115
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0114
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0112
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0111
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0111
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0111
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0110
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0111
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0112
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0113
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0114
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0115
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0116
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0117
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0118
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0118 - val_accuracy: 0.3510 - val_loss: 2.0950

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 638ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 969us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:23[0m 872ms/step
[1m 52/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 987us/step  
[1m111/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 913us/step
[1m161/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 942us/step
[1m212/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 951us/step
[1m264/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 954us/step
[1m318/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 951us/step
[1m371/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 952us/step
[1m426/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 951us/step
[1m479/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 950us/step
[1m534/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 946us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 48/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m107/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 946us/step
[1m157/158[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 966us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 33.39 [%]
Global F1 score (validation) = 32.23 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.01147919 0.00987268 0.01743906 ... 0.02437498 0.04095696 0.00951619]
 [0.00323291 0.00228845 0.00322831 ... 0.11085752 0.00858185 0.00603816]
 [0.00490106 0.00101058 0.00057415 ... 0.00292812 0.00159842 0.00052059]
 ...
 [0.12266155 0.07512508 0.16661744 ... 0.01663233 0.11731124 0.09824768]
 [0.15250368 0.08638918 0.12922242 ... 0.02569597 0.10951281 0.06466426]
 [0.13361394 0.08062405 0.15368114 ... 0.01313458 0.17467366 0.07638507]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 39.92 [%]
Global accuracy score (test) = 28.21 [%]
Global F1 score (train) = 38.8 [%]
Global F1 score (test) = 26.9 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.32      0.53      0.40       184
 CAMINAR CON MÓVIL O LIBRO       0.21      0.24      0.22       184
       CAMINAR USUAL SPEED       0.21      0.18      0.19       184
            CAMINAR ZIGZAG       0.19      0.09      0.12       184
          DE PIE BARRIENDO       0.29      0.22      0.25       184
   DE PIE DOBLANDO TOALLAS       0.36      0.25      0.29       184
    DE PIE MOVIENDO LIBROS       0.33      0.19      0.24       184
          DE PIE USANDO PC       0.15      0.18      0.17       184
        FASE REPOSO CON K5       0.33      0.62      0.43       184
INCREMENTAL CICLOERGOMETRO       0.43      0.49      0.46       184
           SENTADO LEYENDO       0.22      0.19      0.20       184
         SENTADO USANDO PC       0.16      0.04      0.06       184
      SENTADO VIENDO LA TV       0.17      0.21      0.19       184
   SUBIR Y BAJAR ESCALERAS       0.24      0.33      0.27       184
                    TROTAR       0.55      0.49      0.52       161

                  accuracy                           0.28      2737
                 macro avg       0.28      0.28      0.27      2737
              weighted avg       0.28      0.28      0.27      2737


Accuracy capturado en la ejecución 16: 28.21 [%]
F1-score capturado en la ejecución 16: 26.9 [%]

=== EJECUCIÓN 17 ===

--- TRAIN (ejecución 17) ---

--- TEST (ejecución 17) ---
2025-11-07 13:17:09.447052: 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`.
2025-11-07 13:17:09.458491: 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 00:00:1762517829.471598 2802084 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517829.475748 2802084 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517829.485503 2802084 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517829.485523 2802084 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517829.485525 2802084 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517829.485526 2802084 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:17:09.488694: 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 00:00:1762517831.790896 2802084 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517834.882434 2802212 service.cc:152] XLA service 0x76a60801f120 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517834.882468 2802212 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:17:14.946502: 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 00:00:1762517835.366552 2802212 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517837.890703 2802212 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:17[0m 5s/step - accuracy: 0.1250 - loss: 3.3747
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0849 - loss: 3.3585    
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0775 - loss: 3.3415
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0768 - loss: 3.3198
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0776 - loss: 3.3043
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0790 - loss: 3.2914
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0803 - loss: 3.2797
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0817 - loss: 3.2699
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0837 - loss: 3.2590
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0854 - loss: 3.2498
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0872 - loss: 3.2396
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0887 - loss: 3.2309
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0900 - loss: 3.2232
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0917 - loss: 3.2144
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0930 - loss: 3.2067
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0942 - loss: 3.1997
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0955 - loss: 3.1922
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0968 - loss: 3.1849
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0978 - loss: 3.1790
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0989 - loss: 3.1726
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1000 - loss: 3.1660
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1012 - loss: 3.1589
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1022 - loss: 3.1524
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1032 - loss: 3.1460
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1042 - loss: 3.1404
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1050 - loss: 3.1351
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1058 - loss: 3.1298
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1066 - loss: 3.1245
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1075 - loss: 3.1193
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1083 - loss: 3.1144
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1091 - loss: 3.1092
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1099 - loss: 3.1041
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1106 - loss: 3.0995
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1114 - loss: 3.0949
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1120 - loss: 3.0906
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1127 - loss: 3.0862
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1134 - loss: 3.0819
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1141 - loss: 3.0774
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1148 - loss: 3.0731
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1155 - loss: 3.0685
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1162 - loss: 3.0640
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1169 - loss: 3.0597
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1175 - loss: 3.0559
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1179 - loss: 3.0533
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1179 - loss: 3.0531 - val_accuracy: 0.2539 - val_loss: 2.3633
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1250 - loss: 2.9860
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1389 - loss: 2.7708  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1554 - loss: 2.7098
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1637 - loss: 2.6771
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1687 - loss: 2.6639
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1710 - loss: 2.6578
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1719 - loss: 2.6549
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1725 - loss: 2.6535
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.6527
[1m 255/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1740 - loss: 2.6515
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1744 - loss: 2.6502
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1749 - loss: 2.6492
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1752 - loss: 2.6482
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1754 - loss: 2.6475
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1756 - loss: 2.6466
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1757 - loss: 2.6456
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1758 - loss: 2.6442
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1760 - loss: 2.6431
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1761 - loss: 2.6418
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1763 - loss: 2.6405
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1764 - loss: 2.6393
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1766 - loss: 2.6380
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1768 - loss: 2.6368
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1770 - loss: 2.6355
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1772 - loss: 2.6344
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1774 - loss: 2.6334
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1776 - loss: 2.6324
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1778 - loss: 2.6315
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6305
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1782 - loss: 2.6295
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1784 - loss: 2.6286
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1786 - loss: 2.6278
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1788 - loss: 2.6270
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1789 - loss: 2.6261
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1791 - loss: 2.6252
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.6243
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.6234
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6225
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6218
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.6209
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1800 - loss: 2.6202
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1801 - loss: 2.6191
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1803 - loss: 2.6182
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6180 - val_accuracy: 0.2752 - val_loss: 2.2662
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3805
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2090 - loss: 2.5428  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1963 - loss: 2.5750
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1932 - loss: 2.5745
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1927 - loss: 2.5690
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1914 - loss: 2.5655
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1910 - loss: 2.5609
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1913 - loss: 2.5547
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1917 - loss: 2.5485
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1925 - loss: 2.5423
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1933 - loss: 2.5370
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1938 - loss: 2.5327
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1940 - loss: 2.5303
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1943 - loss: 2.5275
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1946 - loss: 2.5248
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1951 - loss: 2.5218
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1955 - loss: 2.5197
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1959 - loss: 2.5174
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1962 - loss: 2.5156
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1965 - loss: 2.5140
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1968 - loss: 2.5125
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1972 - loss: 2.5112
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1975 - loss: 2.5100
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1978 - loss: 2.5087
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1982 - loss: 2.5074
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1985 - loss: 2.5062
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1988 - loss: 2.5051
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1991 - loss: 2.5040
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1993 - loss: 2.5031
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1995 - loss: 2.5020
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1998 - loss: 2.5010
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2000 - loss: 2.5001
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2002 - loss: 2.4992
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2004 - loss: 2.4982
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2006 - loss: 2.4974
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2008 - loss: 2.4967
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.4959
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2012 - loss: 2.4951
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2014 - loss: 2.4943
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2016 - loss: 2.4936
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2018 - loss: 2.4928
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2019 - loss: 2.4920
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2021 - loss: 2.4913
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2022 - loss: 2.4909 - val_accuracy: 0.3077 - val_loss: 2.2181
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 2.4462
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2425 - loss: 2.4045  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2272 - loss: 2.4003
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2194 - loss: 2.3979
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4014
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2145 - loss: 2.4019
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2131 - loss: 2.4027
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2121 - loss: 2.4042
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2117 - loss: 2.4059
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2116 - loss: 2.4073
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2117 - loss: 2.4087
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2121 - loss: 2.4094
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2126 - loss: 2.4094
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2133 - loss: 2.4088
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2140 - loss: 2.4081
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2145 - loss: 2.4077
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2150 - loss: 2.4074
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2154 - loss: 2.4073
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2158 - loss: 2.4071
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2162 - loss: 2.4069
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4066
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4065
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2168 - loss: 2.4063
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4061
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2173 - loss: 2.4059
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2174 - loss: 2.4058
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2175 - loss: 2.4056
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4054
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4052
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4050
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4048
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2179 - loss: 2.4046
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4043
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2181 - loss: 2.4040
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4038
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4035
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4033
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4031
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2185 - loss: 2.4029
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4026
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4023
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4021
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4018
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2190 - loss: 2.4016 - val_accuracy: 0.3057 - val_loss: 2.2157
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.5073
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2051 - loss: 2.4616  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4082
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2256 - loss: 2.3838
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2305 - loss: 2.3662
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2326 - loss: 2.3573
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3509
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3478
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3462
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2339 - loss: 2.3448
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3434
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3423
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3413
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3406
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2350 - loss: 2.3398
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2352 - loss: 2.3391
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2354 - loss: 2.3384
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3379
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2357 - loss: 2.3376
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2358 - loss: 2.3373
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2358 - loss: 2.3371
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2358 - loss: 2.3369
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2358 - loss: 2.3369
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3367
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2354 - loss: 2.3368
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2352 - loss: 2.3368
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2350 - loss: 2.3369
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2347 - loss: 2.3371
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2345 - loss: 2.3372
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3372
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3372
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.3372
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.3371
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3370
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3369
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3368
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3366
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3365
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3363
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3361
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3359
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3357
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3355
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3355 - val_accuracy: 0.3188 - val_loss: 2.1968
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.6386
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2398 - loss: 2.3184  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2418 - loss: 2.3114
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2467 - loss: 2.3011
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2484 - loss: 2.2954
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2952
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.2945
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2938
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2493 - loss: 2.2933
[1m 257/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2932
[1m 283/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.2934
[1m 310/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2937
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2500 - loss: 2.2944
[1m 366/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2950
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2957
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2959
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.2959
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.2959
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2958
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2957
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2494 - loss: 2.2958
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2959
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2960
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2489 - loss: 2.2961
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2962
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2961
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2960
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2958
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2956
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2952
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2950
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2948
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2946
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2944
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2942
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2940
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2938
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2938
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2937
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2936
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2935
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2935
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2484 - loss: 2.2935 - val_accuracy: 0.3256 - val_loss: 2.1313
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 26ms/step - accuracy: 0.5000 - loss: 1.8486
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2846  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2506 - loss: 2.2922
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2871
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2508 - loss: 2.2815
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2773
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2762
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2756
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2514 - loss: 2.2741
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2517 - loss: 2.2729
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2522 - loss: 2.2714
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2526 - loss: 2.2702
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2530 - loss: 2.2694
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2686
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2675
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2667
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2658
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2650
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2640
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2630
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2622
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2614
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2567 - loss: 2.2608
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2570 - loss: 2.2603
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2573 - loss: 2.2599
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2595
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2577 - loss: 2.2593
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2590
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2580 - loss: 2.2588
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2587
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2586
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2585
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2584
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2583
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2586 - loss: 2.2582
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2586 - loss: 2.2581
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2580
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2579
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2579
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2579
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2578
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2578
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2577
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2577 - val_accuracy: 0.3317 - val_loss: 2.1347
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.4549
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2133 - loss: 2.3817  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2283 - loss: 2.3439
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2382 - loss: 2.3120
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2426 - loss: 2.2966
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2458 - loss: 2.2870
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2489 - loss: 2.2801
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2750
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2525 - loss: 2.2710
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2536 - loss: 2.2682
[1m 283/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2650
[1m 310/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2624
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2601
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2566 - loss: 2.2581
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2571 - loss: 2.2559
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2543
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2526
[1m 476/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2514
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2503
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2495
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2489
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2486
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2481
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2478
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2475
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2473
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2469
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2466
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2462
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2458
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2455
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2451
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2582 - loss: 2.2448
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2445
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2441
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2438
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2435
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2432
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2428
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2425
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2586 - loss: 2.2422
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2419
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2415
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2415 - val_accuracy: 0.3232 - val_loss: 2.1292
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0323
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2631 - loss: 2.1610  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1601
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2752 - loss: 2.1742
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2756 - loss: 2.1828
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2739 - loss: 2.1911
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 2.1972
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2720 - loss: 2.2011
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.2040
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2710 - loss: 2.2059
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2708 - loss: 2.2072
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2083
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2700 - loss: 2.2094
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2698 - loss: 2.2097
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2697 - loss: 2.2099
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2697 - loss: 2.2098
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2698 - loss: 2.2096
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2700 - loss: 2.2092
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2702 - loss: 2.2087
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2702 - loss: 2.2084
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2081
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.2079
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.2077
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.2074
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2071
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2068
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2066
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2064
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2061
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.2059
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.2057
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.2054
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.2050
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.2048
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2046
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2044
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2042
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2040
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2038
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2037
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2035
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2033
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2031
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2031 - val_accuracy: 0.3310 - val_loss: 2.1121
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2104
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2856 - loss: 2.0998  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1010
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1039
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1109
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1167
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2792 - loss: 2.1213
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1264
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1302
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1341
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2760 - loss: 2.1368
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2754 - loss: 2.1398
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2750 - loss: 2.1424
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2747 - loss: 2.1442
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2745 - loss: 2.1460
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2743 - loss: 2.1475
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2742 - loss: 2.1489
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1501
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2739 - loss: 2.1516
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2737 - loss: 2.1532
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2735 - loss: 2.1544
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.1553
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2732 - loss: 2.1562
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2732 - loss: 2.1569
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2731 - loss: 2.1575
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2731 - loss: 2.1581
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2731 - loss: 2.1585
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1590
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1595
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 2.1600
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2728 - loss: 2.1605
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1609
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1613
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1616
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1620
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1624
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1627
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1629
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1632
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1634
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1636
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1638
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1640
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2724 - loss: 2.1642
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2724 - loss: 2.1642 - val_accuracy: 0.3242 - val_loss: 2.1001
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.9974
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3126 - loss: 2.1152  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3079 - loss: 2.1133
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3033 - loss: 2.1162
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1158
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2973 - loss: 2.1192
[1m 153/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1210
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1233
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1264
[1m 233/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1282
[1m 260/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2911 - loss: 2.1295
[1m 288/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2906 - loss: 2.1309
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2901 - loss: 2.1327
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2898 - loss: 2.1338
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1345
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2895 - loss: 2.1351
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1358
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1362
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1366
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2887 - loss: 2.1369
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2886 - loss: 2.1372
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1373
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1374
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1375
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1375
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1375
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1377
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1377
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1377
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1377
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1376
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1375
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1374
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1374
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2881 - loss: 2.1375
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2880 - loss: 2.1376
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2880 - loss: 2.1377
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1379
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1379
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1380
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1381
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1382
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2875 - loss: 2.1383
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2874 - loss: 2.1385
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1385 - val_accuracy: 0.3482 - val_loss: 2.0952
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0844
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1047  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1068
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1150
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1191
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1193
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2872 - loss: 2.1191
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1192
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1188
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1186
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1186
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1185
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2886 - loss: 2.1185
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1182
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1178
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1176
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1176
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1177
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1179
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1182
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1185
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1187
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1189
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1190
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1192
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1193
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1194
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1196
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1197
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1198
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1199
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1201
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1203
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1205
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1207
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1209
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1211
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1213
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1215
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1216
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1218
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1218
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1219
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1220 - val_accuracy: 0.3514 - val_loss: 2.1157
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.8304
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0816  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3020 - loss: 2.1110
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3012 - loss: 2.1196
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1207
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.1217
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1208
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1195
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1178
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1163
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1150
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 2.1144
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1144
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1143
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1140
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1137
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1134
[1m 476/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1131
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2936 - loss: 2.1127
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1123
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 2.1120
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1117
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1115
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1114
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1113
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1113
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1112
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1110
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1108
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1106
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1104
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1101
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1099
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1098
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1095
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1093
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1091
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1089
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2948 - loss: 2.1087
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1086
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1085
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1083
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1082
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1081 - val_accuracy: 0.3474 - val_loss: 2.0892
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.1090
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3212 - loss: 2.1621  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3251 - loss: 2.1227
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3228 - loss: 2.1159
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3198 - loss: 2.1137
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 2.1136
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.1148
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.1137
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 2.1122
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3093 - loss: 2.1106
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3088 - loss: 2.1089
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3085 - loss: 2.1077
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3083 - loss: 2.1061
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3081 - loss: 2.1048
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 2.1035
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3079 - loss: 2.1021
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3078 - loss: 2.1011
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3076 - loss: 2.1003
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3073 - loss: 2.0997
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0991
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0985
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0980
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0975
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0970
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0964
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0957
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0951
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0946
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0942
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0939
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0936
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0933
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0931
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0928
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3049 - loss: 2.0926
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0924
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0922
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0920
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0918
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0915
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0912
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0909
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0907
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0906 - val_accuracy: 0.3478 - val_loss: 2.1049
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.3984
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3146 - loss: 2.1876  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3121 - loss: 2.1548
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.1309
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3093 - loss: 2.1170
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 2.1069
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0997
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0935
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0881
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0847
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0817
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0786
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0763
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0745
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0730
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0721
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0716
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0711
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0704
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0699
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0696
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0692
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0689
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0685
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0681
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0677
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0673
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0669
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0665
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0661
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0657
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0653
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0649
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0646
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0643
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0641
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0638
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0636
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0634
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0633
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0631
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0629
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0628 - val_accuracy: 0.3452 - val_loss: 2.0889
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.5000 - loss: 1.7158
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3337 - loss: 1.9764  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0139
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0201
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0196
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0213
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0227
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0245
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0254
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0260
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 2.0268
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3188 - loss: 2.0277
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 2.0287
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0295
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0304
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0312
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0322
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3165 - loss: 2.0330
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 2.0340
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 2.0349
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0355
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0360
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0364
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0366
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0368
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0370
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0371
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3148 - loss: 2.0373
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3148 - loss: 2.0375
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0377
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0379
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0380
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0381
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0382
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0384
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0386
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0387
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0389
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0390
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0391
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0393
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0394
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0395
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0396 - val_accuracy: 0.3472 - val_loss: 2.1231
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.3125 - loss: 1.9663
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3398 - loss: 1.9989  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3361 - loss: 1.9990
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3356 - loss: 1.9951
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.9913
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3354 - loss: 1.9930
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.9959
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 1.9972
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 1.9987
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3326 - loss: 2.0003
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0024
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3308 - loss: 2.0039
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3300 - loss: 2.0053
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3291 - loss: 2.0071
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3282 - loss: 2.0091
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0107
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3272 - loss: 2.0118
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0128
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0134
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0141
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0149
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0154
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0157
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0159
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0161
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0163
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0164
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0166
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0168
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0169
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0170
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 2.0173
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0176
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0178
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0181
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0183
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0186
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0188
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0191
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0192
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0194
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0196
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0197
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0198 - val_accuracy: 0.3599 - val_loss: 2.1039
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1075
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2779 - loss: 2.0169  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0130
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0226
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0263
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0284
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0297
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0294
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0295
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3177 - loss: 2.0300
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0304
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3177 - loss: 2.0304
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0300
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 2.0296
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 2.0288
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0281
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0275
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0269
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0264
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0258
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0253
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0249
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0243
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0240
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0237
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0234
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0231
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0228
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0225
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0221
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3215 - loss: 2.0217
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0214
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0210
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0206
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0203
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0199
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0195
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0191
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0187
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0183
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0179
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0175
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0172
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0171 - val_accuracy: 0.3448 - val_loss: 2.1145
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8432
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1821  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1368
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1113
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0944
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0788
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0683
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0595
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0523
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0464
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0417
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 2.0373
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0338
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0309
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 2.0282
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0257
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0241
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0224
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0209
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0198
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0188
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0177
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0167
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0157
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0149
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0141
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0135
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0129
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0123
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0119
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0116
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0113
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0111
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0108
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0105
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0103
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0100
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0098
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0095
[1m1076/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0092
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0088
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0085
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0083 - val_accuracy: 0.3369 - val_loss: 2.1498
Epoch 20/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.1939
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2908 - loss: 2.0491  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0130
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0049
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3166 - loss: 2.0025
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 1.9986
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 1.9966
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 1.9965
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3215 - loss: 1.9962
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 1.9968
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3226 - loss: 1.9974
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3231 - loss: 1.9978
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3236 - loss: 1.9977
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 1.9970
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 1.9965
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 1.9961
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3255 - loss: 1.9959
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3257 - loss: 1.9959
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3260 - loss: 1.9960
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3261 - loss: 1.9960
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 1.9960
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 1.9960
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 1.9960
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 1.9959
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 1.9958
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 1.9958
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3269 - loss: 1.9956
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3271 - loss: 1.9954
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3272 - loss: 1.9952
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 1.9950
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3274 - loss: 1.9947
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 1.9944
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 1.9941
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3278 - loss: 1.9937
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 1.9934
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3281 - loss: 1.9932
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3283 - loss: 1.9929
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 1.9926
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3285 - loss: 1.9923
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3286 - loss: 1.9921
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3287 - loss: 1.9919
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3289 - loss: 1.9916
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3290 - loss: 1.9913
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3291 - loss: 1.9910
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3291 - loss: 1.9910 - val_accuracy: 0.3365 - val_loss: 2.1204

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 642ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 946us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:15[0m 859ms/step
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m106/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 957us/step
[1m155/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 981us/step
[1m208/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 975us/step
[1m256/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 987us/step
[1m311/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 977us/step
[1m367/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 966us/step
[1m422/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 959us/step
[1m480/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 949us/step
[1m530/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 954us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 53/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 962us/step
[1m106/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 956us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 35.1 [%]
Global F1 score (validation) = 34.08 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.01886094 0.00967761 0.01316597 ... 0.02623405 0.0402401  0.01552448]
 [0.00250733 0.00086511 0.00233765 ... 0.14262958 0.00685919 0.00337181]
 [0.00053369 0.00035454 0.0001992  ... 0.00108137 0.00035577 0.00083103]
 ...
 [0.13944092 0.04979903 0.17791194 ... 0.00479647 0.16455895 0.1557527 ]
 [0.15365945 0.06827072 0.09299019 ... 0.01524714 0.10731602 0.11950342]
 [0.13946092 0.06096834 0.19082926 ... 0.00737472 0.14487673 0.08950949]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 39.53 [%]
Global accuracy score (test) = 27.15 [%]
Global F1 score (train) = 38.85 [%]
Global F1 score (test) = 26.04 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.28      0.53      0.36       184
 CAMINAR CON MÓVIL O LIBRO       0.13      0.09      0.11       184
       CAMINAR USUAL SPEED       0.27      0.13      0.18       184
            CAMINAR ZIGZAG       0.24      0.29      0.27       184
          DE PIE BARRIENDO       0.26      0.13      0.17       184
   DE PIE DOBLANDO TOALLAS       0.30      0.33      0.31       184
    DE PIE MOVIENDO LIBROS       0.22      0.17      0.20       184
          DE PIE USANDO PC       0.15      0.26      0.19       184
        FASE REPOSO CON K5       0.40      0.60      0.48       184
INCREMENTAL CICLOERGOMETRO       0.51      0.38      0.44       184
           SENTADO LEYENDO       0.14      0.12      0.13       184
         SENTADO USANDO PC       0.19      0.04      0.07       184
      SENTADO VIENDO LA TV       0.18      0.33      0.23       184
   SUBIR Y BAJAR ESCALERAS       0.40      0.22      0.28       184
                    TROTAR       0.49      0.47      0.48       161

                  accuracy                           0.27      2737
                 macro avg       0.28      0.27      0.26      2737
              weighted avg       0.28      0.27      0.26      2737


Accuracy capturado en la ejecución 17: 27.15 [%]
F1-score capturado en la ejecución 17: 26.04 [%]

=== EJECUCIÓN 18 ===

--- TRAIN (ejecución 18) ---

--- TEST (ejecución 18) ---
2025-11-07 13:18:26.031546: 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`.
2025-11-07 13:18:26.043754: 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 00:00:1762517906.057989 2805394 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517906.062238 2805394 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517906.072929 2805394 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517906.072951 2805394 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517906.072953 2805394 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517906.072955 2805394 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:18:26.076290: 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 00:00:1762517908.342656 2805394 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762517911.406087 2805524 service.cc:152] XLA service 0x7b897802c8d0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762517911.406132 2805524 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:18:31.478680: 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 00:00:1762517911.916896 2805524 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762517914.446913 2805524 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:10[0m 5s/step - accuracy: 0.0625 - loss: 3.4452
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0744 - loss: 3.4610    
[1m  45/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0668 - loss: 3.4468
[1m  69/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0675 - loss: 3.4096
[1m  92/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0701 - loss: 3.3830
[1m 117/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0726 - loss: 3.3553
[1m 145/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0751 - loss: 3.3311
[1m 172/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0773 - loss: 3.3110
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0795 - loss: 3.2937
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0814 - loss: 3.2793
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0832 - loss: 3.2653
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0846 - loss: 3.2542
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0864 - loss: 3.2432
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0881 - loss: 3.2333
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0896 - loss: 3.2242
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0910 - loss: 3.2157
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0924 - loss: 3.2069
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0937 - loss: 3.1987
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0947 - loss: 3.1921
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0957 - loss: 3.1857
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0967 - loss: 3.1788
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0979 - loss: 3.1713
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0991 - loss: 3.1641
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1003 - loss: 3.1570
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1015 - loss: 3.1500
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1025 - loss: 3.1440
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1035 - loss: 3.1372
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1045 - loss: 3.1312
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1054 - loss: 3.1253
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1063 - loss: 3.1197
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1073 - loss: 3.1135
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1082 - loss: 3.1077
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1091 - loss: 3.1019
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1099 - loss: 3.0966
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1108 - loss: 3.0911
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1115 - loss: 3.0865
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1122 - loss: 3.0821
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1130 - loss: 3.0774
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1137 - loss: 3.0728
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1144 - loss: 3.0684
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1151 - loss: 3.0639
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1157 - loss: 3.0598
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1164 - loss: 3.0557
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1166 - loss: 3.0547
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1166 - loss: 3.0545 - val_accuracy: 0.2627 - val_loss: 2.2831
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.5327
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2104 - loss: 2.5295  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2034 - loss: 2.5618
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1976 - loss: 2.5804
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1942 - loss: 2.5934
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1925 - loss: 2.6028
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1915 - loss: 2.6086
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1907 - loss: 2.6130
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1899 - loss: 2.6175
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1891 - loss: 2.6205
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1886 - loss: 2.6225
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1880 - loss: 2.6246
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1874 - loss: 2.6267
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1871 - loss: 2.6281
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1871 - loss: 2.6287
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1870 - loss: 2.6291
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1868 - loss: 2.6295
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1867 - loss: 2.6297
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1865 - loss: 2.6296
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6295
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6290
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6286
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6280
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6275
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6267
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6259
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.6251
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1865 - loss: 2.6244
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1866 - loss: 2.6237
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1867 - loss: 2.6230
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1868 - loss: 2.6222
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1869 - loss: 2.6216
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1870 - loss: 2.6210
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1871 - loss: 2.6204
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1873 - loss: 2.6197
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1874 - loss: 2.6190
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1875 - loss: 2.6182
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1877 - loss: 2.6175
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1878 - loss: 2.6168
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.6160
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1880 - loss: 2.6154
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1881 - loss: 2.6146
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1883 - loss: 2.6139 - val_accuracy: 0.2750 - val_loss: 2.1938
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1438
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1696 - loss: 2.5723  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1829 - loss: 2.5433
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1885 - loss: 2.5356
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1925 - loss: 2.5296
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1953 - loss: 2.5246
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1980 - loss: 2.5178
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2003 - loss: 2.5113
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2015 - loss: 2.5083
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2025 - loss: 2.5057
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2033 - loss: 2.5039
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2039 - loss: 2.5030
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2042 - loss: 2.5026
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2046 - loss: 2.5019
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2049 - loss: 2.5013
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2051 - loss: 2.5006
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2054 - loss: 2.4998
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4986
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2060 - loss: 2.4974
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2064 - loss: 2.4962
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2067 - loss: 2.4950
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2070 - loss: 2.4940
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2074 - loss: 2.4929
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2077 - loss: 2.4918
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2079 - loss: 2.4908
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4897
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2085 - loss: 2.4887
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.4876
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2091 - loss: 2.4866
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2093 - loss: 2.4856
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2096 - loss: 2.4847
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2099 - loss: 2.4836
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2101 - loss: 2.4828
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2104 - loss: 2.4819
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2106 - loss: 2.4810
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2108 - loss: 2.4801
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.4794
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2111 - loss: 2.4787
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.4781
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2113 - loss: 2.4774
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2114 - loss: 2.4767
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2116 - loss: 2.4760
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2117 - loss: 2.4754
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2117 - loss: 2.4751 - val_accuracy: 0.2954 - val_loss: 2.1813
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 2.1720
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2508 - loss: 2.3523  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2361 - loss: 2.3931
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2303 - loss: 2.4088
[1m 117/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2269 - loss: 2.4143
[1m 146/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2254 - loss: 2.4155
[1m 175/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2242 - loss: 2.4161
[1m 204/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2235 - loss: 2.4164
[1m 232/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2231 - loss: 2.4151
[1m 258/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2227 - loss: 2.4138
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2223 - loss: 2.4129
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2221 - loss: 2.4121
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2218 - loss: 2.4111
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2215 - loss: 2.4102
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2214 - loss: 2.4095
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2213 - loss: 2.4090
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4087
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2211 - loss: 2.4083
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2211 - loss: 2.4082
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2210 - loss: 2.4080
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2210 - loss: 2.4078
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2209 - loss: 2.4076
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.4075
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.4074
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.4072
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.4070
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2208 - loss: 2.4070
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2208 - loss: 2.4069
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2208 - loss: 2.4067
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2208 - loss: 2.4065
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2208 - loss: 2.4063
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.4060
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.4058
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.4055
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2210 - loss: 2.4052
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2211 - loss: 2.4048
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4045
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2214 - loss: 2.4041
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2215 - loss: 2.4037
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2217 - loss: 2.4032
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2218 - loss: 2.4027
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2220 - loss: 2.4021
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2221 - loss: 2.4018 - val_accuracy: 0.3145 - val_loss: 2.1514
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.6297
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2937 - loss: 2.3382  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2748 - loss: 2.3452
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2649 - loss: 2.3523
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2592 - loss: 2.3546
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2566 - loss: 2.3544
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2549 - loss: 2.3537
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2537 - loss: 2.3512
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2525 - loss: 2.3488
[1m 257/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2514 - loss: 2.3466
[1m 283/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2503 - loss: 2.3454
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2493 - loss: 2.3444
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2487 - loss: 2.3431
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2481 - loss: 2.3419
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2477 - loss: 2.3407
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2474 - loss: 2.3397
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2472 - loss: 2.3385
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2469 - loss: 2.3378
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2467 - loss: 2.3369
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3362
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2461 - loss: 2.3357
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2458 - loss: 2.3353
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2455 - loss: 2.3350
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2453 - loss: 2.3347
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2451 - loss: 2.3343
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2450 - loss: 2.3340
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2449 - loss: 2.3336
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2448 - loss: 2.3332
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2446 - loss: 2.3330
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2445 - loss: 2.3328
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2445 - loss: 2.3326
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2444 - loss: 2.3323
[1m 873/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2442 - loss: 2.3321
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2441 - loss: 2.3320
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2440 - loss: 2.3318
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2439 - loss: 2.3316
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2438 - loss: 2.3314
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2437 - loss: 2.3312
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.3310
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.3309
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.3307
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3305
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3303
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3302 - val_accuracy: 0.3153 - val_loss: 2.1303
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.3551
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2700 - loss: 2.1998  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2339
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2532
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2656
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2729
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2774
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2536 - loss: 2.2797
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2528 - loss: 2.2815
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2523 - loss: 2.2827
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2521 - loss: 2.2836
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2519 - loss: 2.2842
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2517 - loss: 2.2848
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2515 - loss: 2.2855
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2862
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.2868
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2505 - loss: 2.2874
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.2879
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2500 - loss: 2.2881
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2884
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.2886
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2888
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.2890
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2493 - loss: 2.2891
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2493 - loss: 2.2890
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2888
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2886
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2883
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2881
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2879
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2877
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2493 - loss: 2.2875
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2493 - loss: 2.2873
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2494 - loss: 2.2871
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2495 - loss: 2.2869
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2867
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2497 - loss: 2.2865
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2862
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2858
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2501 - loss: 2.2854
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2502 - loss: 2.2851
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2503 - loss: 2.2847
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.2844
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2505 - loss: 2.2843 - val_accuracy: 0.3167 - val_loss: 2.1087
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.5164
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2266 - loss: 2.3038  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2450 - loss: 2.2745
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2493 - loss: 2.2661
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2639
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2519 - loss: 2.2640
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2525 - loss: 2.2633
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2621
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2625
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2631
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2638
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2639
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2636
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2637
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2637
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2634
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2569 - loss: 2.2627
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2572 - loss: 2.2622
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2616
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2610
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2604
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2598
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2586 - loss: 2.2591
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2586
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2582
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2578
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2575
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2573
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2573
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2573
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2573
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2571
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2568
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2565
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2562
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2560
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2557
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2554
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2552
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2549
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2547
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2544
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2541
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2540 - val_accuracy: 0.3405 - val_loss: 2.1119
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.4767
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3312 - loss: 2.1406  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.1683
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 2.1789
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1842
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2978 - loss: 2.1854
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1879
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2915 - loss: 2.1906
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2887 - loss: 2.1929
[1m 254/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1942
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1949
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1950
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1950
[1m 366/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1948
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1950
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1952
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1953
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1955
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1959
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1964
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1967
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1969
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1971
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1975
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1980
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1983
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1986
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1988
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1990
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2782 - loss: 2.1992
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2780 - loss: 2.1993
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1995
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1995
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2777 - loss: 2.1995
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1994
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2775 - loss: 2.1994
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1993
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1993
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1993
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1993
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1993
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1993
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1992 - val_accuracy: 0.3407 - val_loss: 2.1251
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2500 - loss: 2.2481
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2794  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2575 - loss: 2.2483
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2339
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2256
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2644 - loss: 2.2199
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2655 - loss: 2.2175
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2664 - loss: 2.2156
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.2131
[1m 258/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.2104
[1m 285/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2692 - loss: 2.2085
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2699 - loss: 2.2067
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2049
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2712 - loss: 2.2035
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2017
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.2001
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2731 - loss: 2.1986
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2736 - loss: 2.1973
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2740 - loss: 2.1962
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2743 - loss: 2.1952
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2746 - loss: 2.1946
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2748 - loss: 2.1939
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2750 - loss: 2.1933
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2753 - loss: 2.1926
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2756 - loss: 2.1918
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1911
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2761 - loss: 2.1904
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2762 - loss: 2.1900
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1897
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1894
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1892
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1890
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1889
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1887
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1885
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1883
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1880
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1877
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2775 - loss: 2.1875
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1872
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2777 - loss: 2.1869
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1867
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1866 - val_accuracy: 0.3131 - val_loss: 2.1189
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1457
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1477  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1479
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1513
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1533
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1557
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1549
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1539
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1523
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1509
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1491
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1478
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1471
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1468
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1465
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1467
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1469
[1m 470/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1470
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1470
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1471
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1472
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1474
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1476
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1477
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1479
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1480
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1481
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1482
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1482
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1482
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2869 - loss: 2.1483
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2869 - loss: 2.1483
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1483
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1483
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1484
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1484
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1485
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1485
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2872 - loss: 2.1486
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2872 - loss: 2.1486
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1485
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2874 - loss: 2.1484
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2874 - loss: 2.1484 - val_accuracy: 0.3333 - val_loss: 2.0850
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.5625 - loss: 1.4741
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3076 - loss: 2.0389  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3009 - loss: 2.0784
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0795
[1m  99/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0827
[1m 126/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0871
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0921
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3015 - loss: 2.0950
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.0969
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.0986
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 2.1009
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1028
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1040
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2991 - loss: 2.1050
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 2.1058
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1063
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1067
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1071
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1074
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 2.1077
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 2.1082
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1087
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1091
[1m 644/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1093
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1096
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1098
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1101
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1104
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1107
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1109
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1112
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1114
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1116
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1118
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1120
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1121
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1122
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1124
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1124
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1125
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1127
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1129
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1129 - val_accuracy: 0.3200 - val_loss: 2.0755
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.0922
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1643  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1631
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1557
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1499
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 2.1468
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 2.1427
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1381
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1338
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1311
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1298
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1283
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1274
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1264
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1255
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1251
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1247
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1241
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1235
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1229
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1221
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1213
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1205
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1198
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1191
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1183
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1177
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1172
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1168
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1164
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1161
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1158
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1155
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1153
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1150
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1148
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1145
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1142
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1140
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1137
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1134
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1131
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1130 - val_accuracy: 0.3321 - val_loss: 2.0828
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1526
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0351  
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0468
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3160 - loss: 2.0524
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0565
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0616
[1m 172/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0664
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0691
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0705
[1m 254/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0710
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0712
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0719
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0725
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0727
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0731
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0736
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0738
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0738
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0739
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0741
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0742
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0744
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0745
[1m 644/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0746
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0747
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0749
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0752
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0756
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3100 - loss: 2.0759
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0762
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0765
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0767
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0768
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0770
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0773
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0775
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0777
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0779
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0781
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0782
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0784
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0786
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0786 - val_accuracy: 0.3411 - val_loss: 2.0941
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.7201
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3413 - loss: 2.0680  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3335 - loss: 2.0852
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3285 - loss: 2.0912
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0933
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0913
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0878
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0853
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 2.0848
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3180 - loss: 2.0850
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0848
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3163 - loss: 2.0848
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 2.0848
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0847
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0842
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0838
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0835
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0834
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0831
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0831
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0830
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0829
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0827
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0823
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0819
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0816
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0813
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0810
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0808
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0806
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0803
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0800
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0796
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0793
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0791
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0788
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0785
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0783
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0780
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0778
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0776
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0773
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0770
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0769 - val_accuracy: 0.3355 - val_loss: 2.0889
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0442
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3086 - loss: 2.0370  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0396
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0314
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0308
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0310
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0317
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0312
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0317
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 2.0331
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3165 - loss: 2.0347
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0361
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0370
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3180 - loss: 2.0378
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3183 - loss: 2.0386
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3186 - loss: 2.0392
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 2.0396
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0399
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0401
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0404
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0406
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0408
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0409
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0410
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0411
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0411
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0411
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0410
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0408
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0408
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0408
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0408
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3220 - loss: 2.0408
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0408
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0407
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0406
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0405
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0404
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0402
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0401
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0400
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0400
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0400 - val_accuracy: 0.3446 - val_loss: 2.0823
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.4375 - loss: 1.8338
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3917 - loss: 1.9268  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3728 - loss: 1.9611
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3635 - loss: 1.9896
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3593 - loss: 2.0036
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3561 - loss: 2.0096
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3534 - loss: 2.0141
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3509 - loss: 2.0167
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 2.0179
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3475 - loss: 2.0187
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 2.0194
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3452 - loss: 2.0200
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3446 - loss: 2.0202
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 2.0207
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3434 - loss: 2.0210
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3430 - loss: 2.0216
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3426 - loss: 2.0224
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 2.0230
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3418 - loss: 2.0235
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3415 - loss: 2.0238
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3412 - loss: 2.0241
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3410 - loss: 2.0244
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3408 - loss: 2.0245
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3406 - loss: 2.0246
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3405 - loss: 2.0246
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3403 - loss: 2.0246
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 2.0246
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3400 - loss: 2.0246
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 2.0246
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3398 - loss: 2.0246
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 2.0246
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3395 - loss: 2.0246
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 2.0247
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 2.0248
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3391 - loss: 2.0247
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 2.0247
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3388 - loss: 2.0247
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 2.0248
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3387 - loss: 2.0248
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3386 - loss: 2.0248
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3385 - loss: 2.0249
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3384 - loss: 2.0249
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3383 - loss: 2.0250
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 2.0250
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3382 - loss: 2.0250 - val_accuracy: 0.3445 - val_loss: 2.0743
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0326
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3253 - loss: 1.9424  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3383 - loss: 1.9363
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3430 - loss: 1.9381
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3429 - loss: 1.9455
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3427 - loss: 1.9538
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.9601
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3420 - loss: 1.9644
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3415 - loss: 1.9682
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3411 - loss: 1.9712
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3406 - loss: 1.9744
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 1.9768
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3397 - loss: 1.9791
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3390 - loss: 1.9814
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3385 - loss: 1.9834
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9854
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3373 - loss: 1.9873
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.9892
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3360 - loss: 1.9908
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3354 - loss: 1.9924
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3348 - loss: 1.9941
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 1.9957
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9971
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3332 - loss: 1.9983
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3329 - loss: 1.9993
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3326 - loss: 2.0002
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3323 - loss: 2.0011
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3320 - loss: 2.0020
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3318 - loss: 2.0028
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0034
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3314 - loss: 2.0039
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3312 - loss: 2.0044
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0048
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3309 - loss: 2.0052
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3308 - loss: 2.0056
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0060
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0064
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0067
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 2.0070
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0072
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0074
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3302 - loss: 2.0076
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 2.0077
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3301 - loss: 2.0078 - val_accuracy: 0.3405 - val_loss: 2.1032
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9815
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1404  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0995
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0691
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0549
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0448
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0381
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 2.0340
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0301
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0271
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0247
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0227
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0207
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0187
[1m 393/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0170
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0154
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0141
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0131
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0123
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0117
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0110
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0104
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3272 - loss: 2.0097
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0091
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0086
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0082
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3283 - loss: 2.0078
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3285 - loss: 2.0075
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3287 - loss: 2.0071
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3290 - loss: 2.0067
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3292 - loss: 2.0062
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3294 - loss: 2.0058
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3296 - loss: 2.0054
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3298 - loss: 2.0050
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 2.0047
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 2.0043
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0040
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 2.0037
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0034
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0031
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3308 - loss: 2.0029
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3309 - loss: 2.0027
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 2.0025
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3310 - loss: 2.0024 - val_accuracy: 0.3441 - val_loss: 2.0757
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 1.9798
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0315  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0145
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0004
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 1.9922
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3315 - loss: 1.9905
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.9899
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 1.9903
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.9909
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3345 - loss: 1.9907
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3351 - loss: 1.9903
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 1.9902
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3358 - loss: 1.9903
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3363 - loss: 1.9899
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 1.9897
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3367 - loss: 1.9898
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3368 - loss: 1.9900
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3368 - loss: 1.9901
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3369 - loss: 1.9900
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3371 - loss: 1.9898
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3372 - loss: 1.9897
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3372 - loss: 1.9896
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3373 - loss: 1.9895
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3374 - loss: 1.9894
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3374 - loss: 1.9892
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.9890
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3375 - loss: 1.9888
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.9886
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.9884
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 1.9883
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.9881
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.9879
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3378 - loss: 1.9878
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3378 - loss: 1.9877
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3378 - loss: 1.9877
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9877
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9876
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9876
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.9875
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 1.9875
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3381 - loss: 1.9874
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3381 - loss: 1.9873
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 1.9873
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3382 - loss: 1.9872 - val_accuracy: 0.3300 - val_loss: 2.0955
Epoch 20/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.7050
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3609 - loss: 1.8993  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3601 - loss: 1.9115
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.9209
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.9197
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.9193
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3585 - loss: 1.9201
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3578 - loss: 1.9218
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.9235
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3570 - loss: 1.9260
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3566 - loss: 1.9281
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3563 - loss: 1.9299
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3555 - loss: 1.9322
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3549 - loss: 1.9341
[1m 393/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.9354
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3538 - loss: 1.9363
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3534 - loss: 1.9372
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3530 - loss: 1.9382
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3527 - loss: 1.9388
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3525 - loss: 1.9393
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3523 - loss: 1.9397
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3522 - loss: 1.9402
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3520 - loss: 1.9407
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3518 - loss: 1.9415
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3516 - loss: 1.9420
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3515 - loss: 1.9424
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3513 - loss: 1.9428
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3511 - loss: 1.9433
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3509 - loss: 1.9437
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3508 - loss: 1.9441
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3506 - loss: 1.9445
[1m 873/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3505 - loss: 1.9448
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3504 - loss: 1.9450
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3503 - loss: 1.9453
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3502 - loss: 1.9456
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3501 - loss: 1.9459
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3500 - loss: 1.9462
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3499 - loss: 1.9465
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3498 - loss: 1.9468
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3497 - loss: 1.9470
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.9474
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.9477
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3495 - loss: 1.9477 - val_accuracy: 0.3572 - val_loss: 2.0529
Epoch 21/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.9883
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3137 - loss: 1.9991  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0027
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 1.9985
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 1.9950
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9906
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3350 - loss: 1.9849
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3375 - loss: 1.9801
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3393 - loss: 1.9777
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3403 - loss: 1.9760
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3413 - loss: 1.9744
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3419 - loss: 1.9737
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3425 - loss: 1.9729
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9716
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3441 - loss: 1.9704
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3447 - loss: 1.9695
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.9687
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3454 - loss: 1.9680
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3457 - loss: 1.9673
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3460 - loss: 1.9665
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9659
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3464 - loss: 1.9655
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.9652
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3467 - loss: 1.9650
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3469 - loss: 1.9648
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.9645
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3473 - loss: 1.9643
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3474 - loss: 1.9641
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3476 - loss: 1.9640
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3478 - loss: 1.9638
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3480 - loss: 1.9635
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3481 - loss: 1.9633
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3482 - loss: 1.9631
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3483 - loss: 1.9630
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3484 - loss: 1.9628
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3486 - loss: 1.9627
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3487 - loss: 1.9625
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3488 - loss: 1.9624
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3489 - loss: 1.9623
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3489 - loss: 1.9622
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3490 - loss: 1.9621
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3491 - loss: 1.9620
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3492 - loss: 1.9619
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3492 - loss: 1.9618 - val_accuracy: 0.3276 - val_loss: 2.0856
Epoch 22/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2765
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3448 - loss: 1.9673  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3530 - loss: 1.9502
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3554 - loss: 1.9471
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.9504
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3543 - loss: 1.9520
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3540 - loss: 1.9530
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3535 - loss: 1.9541
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3532 - loss: 1.9543
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3532 - loss: 1.9534
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3534 - loss: 1.9522
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3535 - loss: 1.9514
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3534 - loss: 1.9513
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3531 - loss: 1.9515
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3526 - loss: 1.9520
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3523 - loss: 1.9527
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3520 - loss: 1.9535
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3518 - loss: 1.9542
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3519 - loss: 1.9544
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3519 - loss: 1.9548
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3521 - loss: 1.9548
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3524 - loss: 1.9547
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3525 - loss: 1.9546
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3527 - loss: 1.9545
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3528 - loss: 1.9543
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3530 - loss: 1.9541
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3532 - loss: 1.9539
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3533 - loss: 1.9536
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3534 - loss: 1.9534
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.9532
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.9530
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.9530
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3536 - loss: 1.9529
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.9527
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3537 - loss: 1.9525
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.9523
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3539 - loss: 1.9520
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3539 - loss: 1.9518
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3540 - loss: 1.9515
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3540 - loss: 1.9513
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3541 - loss: 1.9510
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3542 - loss: 1.9508
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3543 - loss: 1.9506 - val_accuracy: 0.3458 - val_loss: 2.0989
Epoch 23/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2055
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3408 - loss: 1.9751  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3493 - loss: 1.9415
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9340
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3448 - loss: 1.9334
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.9349
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3429 - loss: 1.9381
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 1.9400
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3429 - loss: 1.9400
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 1.9400
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3438 - loss: 1.9394
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3442 - loss: 1.9395
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3444 - loss: 1.9398
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3447 - loss: 1.9399
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3448 - loss: 1.9399
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.9399
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3453 - loss: 1.9399
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3456 - loss: 1.9400
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3459 - loss: 1.9400
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9399
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3466 - loss: 1.9396
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3470 - loss: 1.9392
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3475 - loss: 1.9385
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3480 - loss: 1.9378
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3486 - loss: 1.9371
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3491 - loss: 1.9366
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3496 - loss: 1.9360
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3500 - loss: 1.9356
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3504 - loss: 1.9352
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3508 - loss: 1.9348
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3512 - loss: 1.9344
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3515 - loss: 1.9339
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3519 - loss: 1.9335
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3522 - loss: 1.9331
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3526 - loss: 1.9327
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3529 - loss: 1.9323
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3532 - loss: 1.9319
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3535 - loss: 1.9315
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3538 - loss: 1.9311
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3541 - loss: 1.9307
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3544 - loss: 1.9304
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3547 - loss: 1.9301
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3547 - loss: 1.9300 - val_accuracy: 0.3361 - val_loss: 2.1175
Epoch 24/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.8447
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3747 - loss: 1.9612  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3681 - loss: 1.9584
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3679 - loss: 1.9551
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3661 - loss: 1.9545
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3653 - loss: 1.9525
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3638 - loss: 1.9508
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3632 - loss: 1.9485
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3627 - loss: 1.9476
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3622 - loss: 1.9476
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3623 - loss: 1.9472
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3624 - loss: 1.9467
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3623 - loss: 1.9467
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3624 - loss: 1.9461
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3625 - loss: 1.9451
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3625 - loss: 1.9445
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3623 - loss: 1.9442
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3623 - loss: 1.9437
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3624 - loss: 1.9431
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3624 - loss: 1.9424
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3625 - loss: 1.9416
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3627 - loss: 1.9408
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3628 - loss: 1.9400
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3629 - loss: 1.9393
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3631 - loss: 1.9385
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3633 - loss: 1.9378
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3635 - loss: 1.9370
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3637 - loss: 1.9363
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3639 - loss: 1.9356
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3640 - loss: 1.9349
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.9343
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3642 - loss: 1.9337
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3643 - loss: 1.9332
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3644 - loss: 1.9327
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.9321
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3645 - loss: 1.9317
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3646 - loss: 1.9313
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3646 - loss: 1.9310
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3647 - loss: 1.9306
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3647 - loss: 1.9303
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3648 - loss: 1.9298
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3649 - loss: 1.9295
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3649 - loss: 1.9291
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3650 - loss: 1.9288 - val_accuracy: 0.3441 - val_loss: 2.0806
Epoch 25/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.5077
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3892 - loss: 1.7304  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3873 - loss: 1.7663
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3812 - loss: 1.7849
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3803 - loss: 1.7954
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3801 - loss: 1.8018
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3797 - loss: 1.8088
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3801 - loss: 1.8131
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3798 - loss: 1.8184
[1m 257/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3796 - loss: 1.8233
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3794 - loss: 1.8279
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3792 - loss: 1.8322
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3791 - loss: 1.8358
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3789 - loss: 1.8392
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3787 - loss: 1.8419
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.8445
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.8464
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.8483
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.8499
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3786 - loss: 1.8515
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3785 - loss: 1.8526
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.8537
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.8547
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.8557
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.8567
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.8576
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.8585
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3785 - loss: 1.8594
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3784 - loss: 1.8603
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3783 - loss: 1.8611
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3781 - loss: 1.8619
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3780 - loss: 1.8627
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3778 - loss: 1.8635
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3777 - loss: 1.8642
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3775 - loss: 1.8649
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3774 - loss: 1.8655
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3772 - loss: 1.8661
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3771 - loss: 1.8668
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3770 - loss: 1.8674
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3769 - loss: 1.8680
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3768 - loss: 1.8686
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3767 - loss: 1.8691
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3766 - loss: 1.8692 - val_accuracy: 0.3411 - val_loss: 2.1077

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 646ms/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:09[0m 849ms/step
[1m 53/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 964us/step  
[1m106/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 960us/step
[1m168/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 904us/step
[1m228/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 887us/step
[1m285/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 887us/step
[1m337/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 902us/step
[1m391/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 907us/step
[1m445/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 911us/step
[1m502/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 908us/step
[1m556/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 911us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 53/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 968us/step
[1m108/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 941us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 33.65 [%]
Global F1 score (validation) = 32.75 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[1.68000925e-02 1.23289833e-02 2.71774251e-02 ... 1.55195184e-02
  5.27828410e-02 1.36584202e-02]
 [1.48649665e-03 2.67223874e-03 1.54541421e-03 ... 1.47904679e-01
  6.07405324e-03 3.40346713e-03]
 [9.51874244e-04 1.80902396e-04 1.24189377e-04 ... 5.17704291e-03
  6.52224175e-04 2.43319152e-03]
 ...
 [1.03803076e-01 3.70229930e-02 2.29635984e-01 ... 2.29888782e-03
  2.10132465e-01 1.25855044e-01]
 [1.24965556e-01 5.46581782e-02 1.74079299e-01 ... 1.32124238e-02
  8.50566626e-02 1.07527174e-01]
 [1.29681960e-01 4.75531071e-02 2.13207260e-01 ... 4.05507581e-03
  1.76885501e-01 1.12454847e-01]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 40.68 [%]
Global accuracy score (test) = 30.14 [%]
Global F1 score (train) = 40.27 [%]
Global F1 score (test) = 29.71 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.26      0.46      0.33       184
 CAMINAR CON MÓVIL O LIBRO       0.20      0.17      0.18       184
       CAMINAR USUAL SPEED       0.18      0.18      0.18       184
            CAMINAR ZIGZAG       0.30      0.29      0.29       184
          DE PIE BARRIENDO       0.44      0.24      0.31       184
   DE PIE DOBLANDO TOALLAS       0.36      0.29      0.32       184
    DE PIE MOVIENDO LIBROS       0.42      0.26      0.32       184
          DE PIE USANDO PC       0.16      0.14      0.15       184
        FASE REPOSO CON K5       0.38      0.73      0.50       184
INCREMENTAL CICLOERGOMETRO       0.52      0.38      0.44       184
           SENTADO LEYENDO       0.23      0.21      0.22       184
         SENTADO USANDO PC       0.22      0.09      0.13       184
      SENTADO VIENDO LA TV       0.18      0.33      0.23       184
   SUBIR Y BAJAR ESCALERAS       0.34      0.34      0.34       184
                    TROTAR       0.61      0.43      0.51       161

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


Accuracy capturado en la ejecución 18: 30.14 [%]
F1-score capturado en la ejecución 18: 29.71 [%]

=== EJECUCIÓN 19 ===

--- TRAIN (ejecución 19) ---

--- TEST (ejecución 19) ---
2025-11-07 13:19:54.882917: 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`.
2025-11-07 13:19:54.894326: 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 00:00:1762517994.907911 2809296 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762517994.911915 2809296 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762517994.921890 2809296 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517994.921908 2809296 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517994.921910 2809296 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762517994.921911 2809296 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:19:54.925056: 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 00:00:1762517997.167957 2809296 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762518000.256540 2809426 service.cc:152] XLA service 0x70f450020be0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762518000.256575 2809426 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:20:00.320984: 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 00:00:1762518000.761172 2809426 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762518003.303342 2809426 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:37[0m 5s/step - accuracy: 0.1250 - loss: 3.0972
[1m  19/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0851 - loss: 3.3068    
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0751 - loss: 3.3371
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0734 - loss: 3.3342
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0751 - loss: 3.3199
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0773 - loss: 3.3069
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0790 - loss: 3.2968
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0808 - loss: 3.2887
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0824 - loss: 3.2803
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0836 - loss: 3.2728
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0852 - loss: 3.2638
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0866 - loss: 3.2556
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0882 - loss: 3.2456
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0897 - loss: 3.2357
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0910 - loss: 3.2273
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0921 - loss: 3.2197
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0934 - loss: 3.2109
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0947 - loss: 3.2025
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0958 - loss: 3.1944
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0968 - loss: 3.1877
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0978 - loss: 3.1806
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0988 - loss: 3.1738
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0998 - loss: 3.1668
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1007 - loss: 3.1606
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1016 - loss: 3.1542
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1025 - loss: 3.1478
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1033 - loss: 3.1420
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1042 - loss: 3.1360
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1050 - loss: 3.1303
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1058 - loss: 3.1251
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1067 - loss: 3.1197
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1074 - loss: 3.1148
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1081 - loss: 3.1101
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1089 - loss: 3.1054
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1096 - loss: 3.1007
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1103 - loss: 3.0963
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1109 - loss: 3.0920
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1115 - loss: 3.0880
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1121 - loss: 3.0840
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1127 - loss: 3.0804
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1132 - loss: 3.0767
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1138 - loss: 3.0730
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1142 - loss: 3.0704
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 5ms/step - accuracy: 0.1142 - loss: 3.0703 - val_accuracy: 0.2323 - val_loss: 2.3773
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.4857
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1636 - loss: 2.7262  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1723 - loss: 2.6721
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1766 - loss: 2.6493
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1801 - loss: 2.6395
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6361
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1833 - loss: 2.6357
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1837 - loss: 2.6362
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1841 - loss: 2.6363
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.6367
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.6377
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.6389
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1848 - loss: 2.6395
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.6400
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1846 - loss: 2.6409
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1844 - loss: 2.6415
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1844 - loss: 2.6417
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1844 - loss: 2.6417
[1m 482/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.6414
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.6415
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1845 - loss: 2.6415
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1846 - loss: 2.6414
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1846 - loss: 2.6411
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.6409
[1m 644/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.6406
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.6403
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.6400
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.6397
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.6393
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.6388
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.6382
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.6375
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.6369
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.6363
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1849 - loss: 2.6357
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1850 - loss: 2.6351
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1850 - loss: 2.6344
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1851 - loss: 2.6337
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1851 - loss: 2.6330
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1852 - loss: 2.6322
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1852 - loss: 2.6314
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6307
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1853 - loss: 2.6299
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1854 - loss: 2.6294 - val_accuracy: 0.2640 - val_loss: 2.2847
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.4335
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2063 - loss: 2.5026  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2024 - loss: 2.5070
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2044 - loss: 2.4981
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2067 - loss: 2.4919
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2074 - loss: 2.4897
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2076 - loss: 2.4879
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2073 - loss: 2.4867
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2071 - loss: 2.4856
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2073 - loss: 2.4840
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2077 - loss: 2.4824
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2077 - loss: 2.4820
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2077 - loss: 2.4822
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2077 - loss: 2.4827
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2077 - loss: 2.4831
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2076 - loss: 2.4833
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2074 - loss: 2.4838
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2072 - loss: 2.4838
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2071 - loss: 2.4837
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2072 - loss: 2.4835
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2072 - loss: 2.4835
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2074 - loss: 2.4834
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2074 - loss: 2.4834
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.4834
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.4834
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2076 - loss: 2.4832
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2078 - loss: 2.4831
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2079 - loss: 2.4829
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2080 - loss: 2.4828
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2081 - loss: 2.4827
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2081 - loss: 2.4827
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2081 - loss: 2.4826
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2081 - loss: 2.4825
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4824
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4822
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4821
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4820
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4819
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4818
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4818
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4817
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4817
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4816 - val_accuracy: 0.2760 - val_loss: 2.2382
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4495
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2103 - loss: 2.3454  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2073 - loss: 2.3805
[1m  72/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2095 - loss: 2.3988
[1m 100/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2100 - loss: 2.4104
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2085 - loss: 2.4200
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2071 - loss: 2.4269
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2062 - loss: 2.4319
[1m 207/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2060 - loss: 2.4347
[1m 232/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2064 - loss: 2.4365
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2071 - loss: 2.4378
[1m 288/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2075 - loss: 2.4388
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2080 - loss: 2.4392
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2087 - loss: 2.4386
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2094 - loss: 2.4382
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2099 - loss: 2.4379
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2104 - loss: 2.4374
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2109 - loss: 2.4366
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2115 - loss: 2.4357
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2120 - loss: 2.4346
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2125 - loss: 2.4335
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4325
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2134 - loss: 2.4318
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2137 - loss: 2.4312
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2141 - loss: 2.4307
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2143 - loss: 2.4304
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2146 - loss: 2.4300
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2148 - loss: 2.4295
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2151 - loss: 2.4290
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2154 - loss: 2.4285
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2156 - loss: 2.4281
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2159 - loss: 2.4277
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2161 - loss: 2.4273
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4269
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4266
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4263
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2167 - loss: 2.4260
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2168 - loss: 2.4257
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4253
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4251
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2170 - loss: 2.4248
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4246
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4243
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4243 - val_accuracy: 0.2857 - val_loss: 2.1938
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.4619
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2052 - loss: 2.4033  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2041 - loss: 2.4021
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2076 - loss: 2.3909
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2097 - loss: 2.3883
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2113 - loss: 2.3876
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2124 - loss: 2.3867
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2134 - loss: 2.3852
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2145 - loss: 2.3836
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2154 - loss: 2.3824
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2160 - loss: 2.3812
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2166 - loss: 2.3795
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2171 - loss: 2.3779
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.3766
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2182 - loss: 2.3753
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2188 - loss: 2.3741
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.3733
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2196 - loss: 2.3725
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2199 - loss: 2.3718
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2203 - loss: 2.3709
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2206 - loss: 2.3702
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2209 - loss: 2.3695
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.3688
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2216 - loss: 2.3681
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2218 - loss: 2.3676
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2221 - loss: 2.3671
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2224 - loss: 2.3665
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2227 - loss: 2.3660
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.3655
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2232 - loss: 2.3650
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2235 - loss: 2.3645
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2237 - loss: 2.3639
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2240 - loss: 2.3633
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2242 - loss: 2.3628
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2244 - loss: 2.3622
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2246 - loss: 2.3616
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2248 - loss: 2.3611
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2250 - loss: 2.3607
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2252 - loss: 2.3602
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2253 - loss: 2.3597
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3593
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2256 - loss: 2.3589
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2257 - loss: 2.3585
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2258 - loss: 2.3583 - val_accuracy: 0.3059 - val_loss: 2.1536
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.1386
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3032 - loss: 2.2274  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2750 - loss: 2.2578
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2824
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2941
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2996
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2519 - loss: 2.3020
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2505 - loss: 2.3050
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.3060
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.3064
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2492 - loss: 2.3063
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.3058
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.3057
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2484 - loss: 2.3059
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2481 - loss: 2.3065
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2478 - loss: 2.3069
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2477 - loss: 2.3069
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2476 - loss: 2.3068
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2475 - loss: 2.3068
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2474 - loss: 2.3067
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2473 - loss: 2.3066
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2473 - loss: 2.3067
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2471 - loss: 2.3067
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.3066
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.3065
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.3064
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.3064
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.3064
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2467 - loss: 2.3063
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2467 - loss: 2.3063
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2466 - loss: 2.3063
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2466 - loss: 2.3064
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.3064
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.3064
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.3063
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3063
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3063
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3063
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3062
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3061
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3059
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.3057
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.3055
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2465 - loss: 2.3055 - val_accuracy: 0.3113 - val_loss: 2.1504
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0926
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2297 - loss: 2.3187  
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2336 - loss: 2.2985
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.2898
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2401 - loss: 2.2886
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2423 - loss: 2.2907
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2439 - loss: 2.2913
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2908
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2468 - loss: 2.2890
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2869
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2845
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2501 - loss: 2.2827
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.2810
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2515 - loss: 2.2794
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2524 - loss: 2.2776
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2530 - loss: 2.2762
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2748
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2737
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2726
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2716
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2706
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2698
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2692
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2687
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2682
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2677
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2673
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2669
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2666
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2663
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2536 - loss: 2.2660
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2657
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2654
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2651
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2648
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2645
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2643
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2641
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2638
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2533 - loss: 2.2637
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2636
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2635
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2531 - loss: 2.2634
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2531 - loss: 2.2633 - val_accuracy: 0.3258 - val_loss: 2.1292
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.4375 - loss: 2.1499
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3129 - loss: 2.1565  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1838
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1937
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2842 - loss: 2.2003
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 2.2045
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 2.2089
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.2111
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 2.2140
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.2165
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2761 - loss: 2.2185
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2752 - loss: 2.2201
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2747 - loss: 2.2212
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2744 - loss: 2.2217
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2221
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2736 - loss: 2.2223
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.2224
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2731 - loss: 2.2225
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 2.2226
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.2228
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2721 - loss: 2.2230
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2718 - loss: 2.2233
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.2237
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2711 - loss: 2.2241
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.2244
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2246
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2248
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.2248
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.2249
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.2250
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2696 - loss: 2.2251
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.2252
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2693 - loss: 2.2254
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2691 - loss: 2.2256
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2689 - loss: 2.2258
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2260
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2686 - loss: 2.2260
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.2260
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2684 - loss: 2.2261
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.2261
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.2260
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2682 - loss: 2.2261
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2682 - loss: 2.2261
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2682 - loss: 2.2261 - val_accuracy: 0.3405 - val_loss: 2.1132
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2500 - loss: 2.4194
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2482 - loss: 2.3039  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2492
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2649 - loss: 2.2315
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2668 - loss: 2.2267
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2668 - loss: 2.2240
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2661 - loss: 2.2232
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 2.2229
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2645 - loss: 2.2236
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2639 - loss: 2.2239
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2632 - loss: 2.2244
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2244
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2625 - loss: 2.2238
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2625 - loss: 2.2228
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2626 - loss: 2.2215
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2205
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2198
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2188
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2178
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2636 - loss: 2.2168
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2639 - loss: 2.2159
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2153
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2148
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2144
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2141
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2136
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2641 - loss: 2.2131
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2643 - loss: 2.2127
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2644 - loss: 2.2122
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2644 - loss: 2.2118
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2645 - loss: 2.2113
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2646 - loss: 2.2109
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2647 - loss: 2.2105
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2648 - loss: 2.2101
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2649 - loss: 2.2096
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2650 - loss: 2.2091
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2651 - loss: 2.2087
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2653 - loss: 2.2084
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2654 - loss: 2.2080
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2655 - loss: 2.2077
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2656 - loss: 2.2073
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2658 - loss: 2.2070
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2659 - loss: 2.2067
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2659 - loss: 2.2066 - val_accuracy: 0.3502 - val_loss: 2.1012
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1766
[1m  32/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2747 - loss: 2.1578  
[1m  61/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1616
[1m  90/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1608
[1m 117/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1601
[1m 146/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1598
[1m 173/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1595
[1m 201/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1589
[1m 231/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1580
[1m 258/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1573
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1562
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1558
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1559
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1559
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1558
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1554
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1550
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1546
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1543
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1543
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1546
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1549
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1552
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1554
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1557
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1560
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1564
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1567
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1571
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1575
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1578
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1582
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1585
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1588
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1591
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1593
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1596
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1599
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1601
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1603
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1605
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1606
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1607 - val_accuracy: 0.3363 - val_loss: 2.0832
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.0985
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2675 - loss: 2.1414  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2516 - loss: 2.1678
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2481 - loss: 2.1752
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2477 - loss: 2.1779
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2482 - loss: 2.1791
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2488 - loss: 2.1788
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.1778
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2528 - loss: 2.1756
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.1734
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2578 - loss: 2.1717
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2595 - loss: 2.1704
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2610 - loss: 2.1689
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2622 - loss: 2.1679
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2634 - loss: 2.1670
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2646 - loss: 2.1663
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2656 - loss: 2.1657
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2664 - loss: 2.1654
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2671 - loss: 2.1650
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.1642
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.1635
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2692 - loss: 2.1628
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.1622
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.1617
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.1613
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.1609
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2716 - loss: 2.1606
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.1604
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2723 - loss: 2.1602
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1600
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1597
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2732 - loss: 2.1595
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2735 - loss: 2.1594
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2738 - loss: 2.1593
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1592
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2744 - loss: 2.1590
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2746 - loss: 2.1588
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2749 - loss: 2.1586
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2752 - loss: 2.1583
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2755 - loss: 2.1580
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2757 - loss: 2.1578
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2760 - loss: 2.1576
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2762 - loss: 2.1573
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2762 - loss: 2.1573 - val_accuracy: 0.3524 - val_loss: 2.0832
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0540
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3058 - loss: 2.1089  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1182
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1207
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1221
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1232
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1254
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1274
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1277
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2948 - loss: 2.1280
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1282
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1282
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1281
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1284
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1284
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1284
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1282
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2955 - loss: 2.1277
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1271
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2955 - loss: 2.1266
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1263
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1261
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1260
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1258
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1256
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1256
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1256
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1256
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1256
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1256
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1256
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1257
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2938 - loss: 2.1258
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 2.1259
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1259
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1260
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1261
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1262
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1262
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 2.1262
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1262
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1262
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1262
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1262
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1262 - val_accuracy: 0.3456 - val_loss: 2.0695
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.3125 - loss: 2.3058
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3302 - loss: 2.0616  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0741
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0890
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0953
[1m 126/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0975
[1m 152/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0955
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3076 - loss: 2.0936
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3083 - loss: 2.0917
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3083 - loss: 2.0917
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0927
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3073 - loss: 2.0936
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0940
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0942
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0947
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0954
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0961
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0970
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0976
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0981
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0986
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 2.0990
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0994
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0998
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 2.1001
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3041 - loss: 2.1003
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3040 - loss: 2.1004
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 2.1005
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3038 - loss: 2.1006
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3037 - loss: 2.1006
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.1006
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.1006
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.1006
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.1006
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3033 - loss: 2.1007
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3031 - loss: 2.1007
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.1007
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.1008
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.1008
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.1008
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.1009
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.1009
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.1009
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3025 - loss: 2.1009 - val_accuracy: 0.3502 - val_loss: 2.0616
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.5000 - loss: 1.8108
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3346 - loss: 1.9492  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3252 - loss: 1.9966
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3158 - loss: 2.0276
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0458
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0572
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3015 - loss: 2.0665
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0715
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 2.0749
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 2.0766
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 2.0783
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2964 - loss: 2.0799
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2957 - loss: 2.0816
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 2.0827
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 2.0841
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.0853
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 2.0868
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.0877
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2932 - loss: 2.0885
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2929 - loss: 2.0892
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 2.0897
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.0902
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2922 - loss: 2.0907
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2921 - loss: 2.0910
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.0913
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 2.0916
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 2.0916
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 2.0917
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.0917
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.0917
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.0918
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.0919
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.0920
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.0920
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.0921
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.0920
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 2.0920
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.0919
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 2.0919
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.0918
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 2.0917
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.0916
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2931 - loss: 2.0916
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2932 - loss: 2.0916 - val_accuracy: 0.3568 - val_loss: 2.0579
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0985
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3331 - loss: 2.0463  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0708
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3081 - loss: 2.0786
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0829
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0835
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0834
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3086 - loss: 2.0820
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0805
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0795
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0788
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0782
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0777
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0775
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0772
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0770
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0767
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0761
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0755
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0750
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0745
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0741
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0738
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0735
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0733
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0732
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0732
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0732
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0732
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0731
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0732
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0733
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0732
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0732
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0732
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0731
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0730
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0729
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0728
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0726
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0724
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0722
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0720
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0720 - val_accuracy: 0.3452 - val_loss: 2.0198
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4075
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2887 - loss: 2.1066  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0807
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0719
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0684
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0665
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0645
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 2.0623
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0608
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3088 - loss: 2.0596
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0591
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0583
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3100 - loss: 2.0574
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0563
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0554
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0548
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0543
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0539
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0535
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0533
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0531
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0530
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0529
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0528
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0527
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0525
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0524
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0523
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0522
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0521
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0520
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0520
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0520
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0520
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0520
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0520
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0520
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0520
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0520
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0519
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0519
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0518
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0517
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0517 - val_accuracy: 0.3524 - val_loss: 2.0597
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.0549
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2989 - loss: 2.0444  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2951 - loss: 2.0621
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2947 - loss: 2.0627
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 2.0627
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2971 - loss: 2.0627
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 2.0643
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0648
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0650
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0655
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0650
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0641
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0634
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0627
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0623
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0620
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0619
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0617
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0611
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0606
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0601
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0596
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0589
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3079 - loss: 2.0583
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3083 - loss: 2.0577
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3086 - loss: 2.0572
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0566
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0560
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0553
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0546
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0540
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0535
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0531
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0528
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0525
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0522
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0519
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0517
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0514
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0512
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0510
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0508
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3133 - loss: 2.0506
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3133 - loss: 2.0505 - val_accuracy: 0.3617 - val_loss: 2.0701
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0022
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3794 - loss: 1.8677  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3609 - loss: 1.9170
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3536 - loss: 1.9454
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3537 - loss: 1.9544
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3523 - loss: 1.9635
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3511 - loss: 1.9694
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3505 - loss: 1.9721
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3500 - loss: 1.9743
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3490 - loss: 1.9770
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3482 - loss: 1.9790
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3475 - loss: 1.9805
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3466 - loss: 1.9817
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3457 - loss: 1.9831
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3450 - loss: 1.9843
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3442 - loss: 1.9856
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 1.9869
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3422 - loss: 1.9882
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 1.9893
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3406 - loss: 1.9904
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3400 - loss: 1.9913
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3395 - loss: 1.9921
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.9927
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 1.9932
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3386 - loss: 1.9938
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3384 - loss: 1.9944
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 1.9948
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 1.9953
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3377 - loss: 1.9958
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3374 - loss: 1.9963
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3372 - loss: 1.9966
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3370 - loss: 1.9970
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3369 - loss: 1.9973
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3367 - loss: 1.9976
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3365 - loss: 1.9978
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3364 - loss: 1.9980
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 1.9982
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3361 - loss: 1.9985
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 1.9988
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3359 - loss: 1.9991
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3358 - loss: 1.9993
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3356 - loss: 1.9996
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3355 - loss: 1.9999
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3354 - loss: 2.0000 - val_accuracy: 0.3403 - val_loss: 2.0789
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.0166
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3040 - loss: 1.9939  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0034
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3100 - loss: 2.0059
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0062
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0081
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0087
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0085
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0076
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 2.0066
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 2.0066
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3164 - loss: 2.0070
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 2.0071
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 2.0074
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0077
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0080
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0086
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0090
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0093
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0093
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3187 - loss: 2.0092
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0091
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0090
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0089
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0088
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0088
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0087
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0086
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0085
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0083
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0081
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0079
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3227 - loss: 2.0077
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0074
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3231 - loss: 2.0073
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0071
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0069
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0067
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3238 - loss: 2.0065
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0064
[1m1103/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0063
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0062
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0061
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0060 - val_accuracy: 0.3441 - val_loss: 2.0634
Epoch 20/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.6250 - loss: 1.6017
[1m  21/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.4507 - loss: 1.8374  
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4104 - loss: 1.8806
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3920 - loss: 1.9003
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3807 - loss: 1.9138
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3723 - loss: 1.9269
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3666 - loss: 1.9375
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3626 - loss: 1.9444
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3601 - loss: 1.9493
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3579 - loss: 1.9528
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3557 - loss: 1.9565
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3539 - loss: 1.9593
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3524 - loss: 1.9619
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3512 - loss: 1.9642
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3503 - loss: 1.9663
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3496 - loss: 1.9678
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3491 - loss: 1.9691
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3487 - loss: 1.9699
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3483 - loss: 1.9707
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3479 - loss: 1.9714
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3475 - loss: 1.9720
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9726
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3468 - loss: 1.9732
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.9739
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9743
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3459 - loss: 1.9748
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3456 - loss: 1.9753
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.9757
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3451 - loss: 1.9760
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3449 - loss: 1.9764
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3447 - loss: 1.9767
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3445 - loss: 1.9771
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3443 - loss: 1.9774
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3441 - loss: 1.9776
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3439 - loss: 1.9778
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3438 - loss: 1.9780
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3436 - loss: 1.9782
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3434 - loss: 1.9784
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3433 - loss: 1.9785
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3432 - loss: 1.9786
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3431 - loss: 1.9787
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3430 - loss: 1.9789
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3429 - loss: 1.9791
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3428 - loss: 1.9792 - val_accuracy: 0.3649 - val_loss: 2.0901

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m57s[0m 671ms/step
[1m47/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:04[0m 839ms/step
[1m 50/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m106/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 964us/step
[1m157/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 970us/step
[1m213/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 953us/step
[1m267/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 950us/step
[1m327/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 931us/step
[1m376/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 943us/step
[1m425/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 954us/step
[1m478/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 954us/step
[1m528/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 960us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m50/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 51/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m108/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 939us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 34.11 [%]
Global F1 score (validation) = 33.21 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.01144592 0.01402423 0.03058084 ... 0.01398932 0.08216941 0.00967834]
 [0.00480014 0.00351855 0.00350979 ... 0.07207713 0.01018932 0.00718806]
 [0.00067536 0.00055376 0.0005748  ... 0.0017864  0.00102106 0.00048528]
 ...
 [0.16364554 0.0616012  0.23851694 ... 0.00457211 0.12297195 0.12846962]
 [0.18228292 0.05656092 0.17059971 ... 0.01027075 0.07852155 0.14749132]
 [0.07787531 0.06607066 0.30159098 ... 0.00120004 0.16231024 0.12455527]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 43.38 [%]
Global accuracy score (test) = 29.92 [%]
Global F1 score (train) = 43.04 [%]
Global F1 score (test) = 30.31 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.25      0.52      0.34       184
 CAMINAR CON MÓVIL O LIBRO       0.26      0.27      0.26       184
       CAMINAR USUAL SPEED       0.22      0.27      0.24       184
            CAMINAR ZIGZAG       0.18      0.13      0.15       184
          DE PIE BARRIENDO       0.41      0.18      0.25       184
   DE PIE DOBLANDO TOALLAS       0.40      0.31      0.35       184
    DE PIE MOVIENDO LIBROS       0.38      0.22      0.28       184
          DE PIE USANDO PC       0.11      0.19      0.14       184
        FASE REPOSO CON K5       0.45      0.59      0.51       184
INCREMENTAL CICLOERGOMETRO       0.52      0.42      0.47       184
           SENTADO LEYENDO       0.35      0.34      0.34       184
         SENTADO USANDO PC       0.16      0.14      0.15       184
      SENTADO VIENDO LA TV       0.19      0.23      0.21       184
   SUBIR Y BAJAR ESCALERAS       0.35      0.21      0.26       184
                    TROTAR       0.72      0.52      0.60       161

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


Accuracy capturado en la ejecución 19: 29.92 [%]
F1-score capturado en la ejecución 19: 30.31 [%]

=== EJECUCIÓN 20 ===

--- TRAIN (ejecución 20) ---

--- TEST (ejecución 20) ---
2025-11-07 13:21:11.330262: 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`.
2025-11-07 13:21:11.341702: 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 00:00:1762518071.355119 2812602 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762518071.359165 2812602 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762518071.369395 2812602 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518071.369416 2812602 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518071.369418 2812602 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518071.369419 2812602 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:21:11.372729: 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 00:00:1762518073.628410 2812602 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762518076.710591 2812738 service.cc:152] XLA service 0x7882cc002440 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762518076.710649 2812738 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:21:16.775855: 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 00:00:1762518077.199444 2812738 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762518079.705396 2812738 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43:28[0m 5s/step - accuracy: 0.1250 - loss: 2.9430
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0720 - loss: 3.2192    
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0765 - loss: 3.2566
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0822 - loss: 3.2428
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0861 - loss: 3.2337
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0893 - loss: 3.2257
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0914 - loss: 3.2197
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0928 - loss: 3.2128
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0940 - loss: 3.2043
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0950 - loss: 3.1960
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0962 - loss: 3.1878
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0973 - loss: 3.1810
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0983 - loss: 3.1738
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0993 - loss: 3.1667
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1004 - loss: 3.1598
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1015 - loss: 3.1529
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1024 - loss: 3.1467
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1034 - loss: 3.1406
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1043 - loss: 3.1343
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1051 - loss: 3.1285
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1060 - loss: 3.1228
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1068 - loss: 3.1175
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1076 - loss: 3.1124
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1083 - loss: 3.1076
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1090 - loss: 3.1029
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1097 - loss: 3.0983
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1104 - loss: 3.0936
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1111 - loss: 3.0887
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1118 - loss: 3.0841
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1125 - loss: 3.0796
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1132 - loss: 3.0755
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1139 - loss: 3.0705
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1146 - loss: 3.0664
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1153 - loss: 3.0620
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1160 - loss: 3.0577
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1166 - loss: 3.0534
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1173 - loss: 3.0495
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1179 - loss: 3.0456
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1185 - loss: 3.0418
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1191 - loss: 3.0377
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1197 - loss: 3.0339
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1203 - loss: 3.0301
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1207 - loss: 3.0274
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1207 - loss: 3.0273 - val_accuracy: 0.2337 - val_loss: 2.3161
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2500 - loss: 2.6702
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1863 - loss: 2.7024  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1840 - loss: 2.6839
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1835 - loss: 2.6741
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6675
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6628
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1828 - loss: 2.6588
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1830 - loss: 2.6557
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6538
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1825 - loss: 2.6514
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6492
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1821 - loss: 2.6469
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1820 - loss: 2.6447
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1819 - loss: 2.6424
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1818 - loss: 2.6402
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.6385
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1816 - loss: 2.6372
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1814 - loss: 2.6360
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1813 - loss: 2.6348
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1813 - loss: 2.6336
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1814 - loss: 2.6322
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1814 - loss: 2.6309
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1815 - loss: 2.6298
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1815 - loss: 2.6287
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1816 - loss: 2.6276
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1816 - loss: 2.6265
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1816 - loss: 2.6255
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1817 - loss: 2.6246
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1818 - loss: 2.6237
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1819 - loss: 2.6227
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1820 - loss: 2.6217
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1820 - loss: 2.6209
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1821 - loss: 2.6199
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1822 - loss: 2.6191
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6182
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1824 - loss: 2.6173
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1825 - loss: 2.6165
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6157
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6149
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.6141
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1829 - loss: 2.6133
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1830 - loss: 2.6124
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1831 - loss: 2.6117 - val_accuracy: 0.2577 - val_loss: 2.2483
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0000e+00 - loss: 2.9908
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1843 - loss: 2.5333      
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1842 - loss: 2.5091
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1801 - loss: 2.5184
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1803 - loss: 2.5222
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1808 - loss: 2.5223
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1809 - loss: 2.5232
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1817 - loss: 2.5219
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1825 - loss: 2.5199
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1834 - loss: 2.5178
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1840 - loss: 2.5163
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.5147
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1853 - loss: 2.5133
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1859 - loss: 2.5121
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1864 - loss: 2.5113
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1869 - loss: 2.5107
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1873 - loss: 2.5100
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1876 - loss: 2.5093
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1879 - loss: 2.5084
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1883 - loss: 2.5074
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1885 - loss: 2.5067
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1887 - loss: 2.5060
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1890 - loss: 2.5052
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1893 - loss: 2.5044
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1896 - loss: 2.5036
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1899 - loss: 2.5028
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1901 - loss: 2.5021
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1904 - loss: 2.5013
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1907 - loss: 2.5006
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1909 - loss: 2.4999
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1911 - loss: 2.4991
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1913 - loss: 2.4984
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1915 - loss: 2.4976
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1918 - loss: 2.4969
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1920 - loss: 2.4962
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1922 - loss: 2.4957
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1923 - loss: 2.4951
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1925 - loss: 2.4946
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1927 - loss: 2.4941
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1929 - loss: 2.4935
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1931 - loss: 2.4928
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1933 - loss: 2.4922
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1936 - loss: 2.4915
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1937 - loss: 2.4910 - val_accuracy: 0.2710 - val_loss: 2.2034
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.8984
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2466 - loss: 2.2804  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2371 - loss: 2.3326
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2327 - loss: 2.3493
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2284 - loss: 2.3599
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2267 - loss: 2.3640
[1m 151/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2256 - loss: 2.3664
[1m 178/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2243 - loss: 2.3679
[1m 204/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2238 - loss: 2.3683
[1m 230/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2232 - loss: 2.3695
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2229 - loss: 2.3705
[1m 283/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2227 - loss: 2.3718
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3737
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2219 - loss: 2.3754
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2216 - loss: 2.3766
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2213 - loss: 2.3778
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2211 - loss: 2.3791
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2208 - loss: 2.3800
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2206 - loss: 2.3810
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2204 - loss: 2.3819
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2202 - loss: 2.3826
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2200 - loss: 2.3831
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2199 - loss: 2.3835
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2198 - loss: 2.3838
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2198 - loss: 2.3839
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2197 - loss: 2.3839
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2198 - loss: 2.3839
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2198 - loss: 2.3837
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2199 - loss: 2.3835
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2199 - loss: 2.3833
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2200 - loss: 2.3831
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2200 - loss: 2.3829
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2200 - loss: 2.3826
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2201 - loss: 2.3825
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2202 - loss: 2.3823
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2202 - loss: 2.3821
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2204 - loss: 2.3818
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2205 - loss: 2.3816
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2206 - loss: 2.3813
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2207 - loss: 2.3811
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2208 - loss: 2.3810
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.3808
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.3807
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2210 - loss: 2.3807 - val_accuracy: 0.3109 - val_loss: 2.1497
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3182
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2165 - loss: 2.3249  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2178 - loss: 2.3440
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2209 - loss: 2.3438
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2217 - loss: 2.3482
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2214 - loss: 2.3528
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2206 - loss: 2.3567
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2206 - loss: 2.3579
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.3577
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2216 - loss: 2.3575
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2218 - loss: 2.3575
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2221 - loss: 2.3574
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2225 - loss: 2.3575
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2229 - loss: 2.3575
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2232 - loss: 2.3574
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2237 - loss: 2.3569
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2241 - loss: 2.3563
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2245 - loss: 2.3559
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2248 - loss: 2.3556
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2250 - loss: 2.3553
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.3549
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3545
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2256 - loss: 2.3540
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2258 - loss: 2.3534
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2260 - loss: 2.3529
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2261 - loss: 2.3523
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2263 - loss: 2.3518
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2266 - loss: 2.3512
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2268 - loss: 2.3506
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3502
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2271 - loss: 2.3498
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2272 - loss: 2.3495
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2273 - loss: 2.3493
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2274 - loss: 2.3491
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2275 - loss: 2.3489
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2276 - loss: 2.3486
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2277 - loss: 2.3484
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2278 - loss: 2.3481
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2278 - loss: 2.3480
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3478
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3476
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3474
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3472
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3472 - val_accuracy: 0.3192 - val_loss: 2.1702
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.3162
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2127 - loss: 2.3550  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2224 - loss: 2.3126
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2231 - loss: 2.3061
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3068
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3075
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2231 - loss: 2.3062
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2242 - loss: 2.3042
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3016
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2271 - loss: 2.2992
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2288 - loss: 2.2971
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2301 - loss: 2.2957
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2311 - loss: 2.2951
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2317 - loss: 2.2947
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2322 - loss: 2.2945
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2326 - loss: 2.2946
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2328 - loss: 2.2947
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2332 - loss: 2.2945
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2334 - loss: 2.2943
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2336 - loss: 2.2941
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2339 - loss: 2.2939
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2340 - loss: 2.2936
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2342 - loss: 2.2933
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2344 - loss: 2.2930
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2346 - loss: 2.2926
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2348 - loss: 2.2923
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2350 - loss: 2.2922
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2351 - loss: 2.2921
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2352 - loss: 2.2920
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2353 - loss: 2.2919
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2354 - loss: 2.2918
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2355 - loss: 2.2917
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.2917
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2358 - loss: 2.2916
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2360 - loss: 2.2915
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2362 - loss: 2.2914
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2364 - loss: 2.2912
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2366 - loss: 2.2911
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2368 - loss: 2.2910
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2369 - loss: 2.2909
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2371 - loss: 2.2908
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2372 - loss: 2.2907
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2374 - loss: 2.2907
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2374 - loss: 2.2906 - val_accuracy: 0.3452 - val_loss: 2.1193
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.2893
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2445 - loss: 2.2729  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2364 - loss: 2.2968
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3019
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3008
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2327 - loss: 2.3005
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3001
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2338 - loss: 2.2990
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2348 - loss: 2.2969
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2353 - loss: 2.2957
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.2938
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2367 - loss: 2.2919
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2371 - loss: 2.2903
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2375 - loss: 2.2889
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.2877
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2383 - loss: 2.2865
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2386 - loss: 2.2852
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2388 - loss: 2.2841
[1m 482/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2391 - loss: 2.2829
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2394 - loss: 2.2820
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2396 - loss: 2.2813
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2399 - loss: 2.2807
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2402 - loss: 2.2800
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2405 - loss: 2.2793
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2408 - loss: 2.2788
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2412 - loss: 2.2782
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2414 - loss: 2.2778
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2417 - loss: 2.2774
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2419 - loss: 2.2771
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2421 - loss: 2.2768
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2423 - loss: 2.2764
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.2760
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2757
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2429 - loss: 2.2754
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.2751
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2748
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.2744
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.2741
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2437 - loss: 2.2738
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2438 - loss: 2.2735
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2439 - loss: 2.2731
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2440 - loss: 2.2727
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2441 - loss: 2.2723
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2442 - loss: 2.2720 - val_accuracy: 0.3313 - val_loss: 2.1215
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.2500 - loss: 2.3192
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2271 - loss: 2.2777  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2364 - loss: 2.2590
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2391 - loss: 2.2530
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2406 - loss: 2.2517
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2421 - loss: 2.2507
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2421 - loss: 2.2507
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2491
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2443 - loss: 2.2476
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.2468
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.2459
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2468 - loss: 2.2450
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2476 - loss: 2.2441
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2427
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2418
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2410
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.2403
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2398
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2392
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2387
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2517 - loss: 2.2381
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2521 - loss: 2.2377
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2525 - loss: 2.2374
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2528 - loss: 2.2371
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2367
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2364
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2362
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2359
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2354
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2351
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2547 - loss: 2.2348
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2346
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2343
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2340
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2338
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2335
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2332
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2330
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2328
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2326
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2324
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2322
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2565 - loss: 2.2320
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2566 - loss: 2.2320 - val_accuracy: 0.3308 - val_loss: 2.1518
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 23ms/step - accuracy: 0.1875 - loss: 2.0148
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1224  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1588
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1749
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1836
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2911 - loss: 2.1879
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2903 - loss: 2.1888
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2887 - loss: 2.1896
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1902
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1907
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1904
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1900
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1901
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1903
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1904
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1906
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1906
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1907
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1909
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1910
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1909
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1910
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1910
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1912
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1913
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2786 - loss: 2.1914
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1915
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2780 - loss: 2.1915
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1916
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1916
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1915
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1915
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1914
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1914
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1914
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1913
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1913
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1913
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2763 - loss: 2.1912
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2762 - loss: 2.1912
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2761 - loss: 2.1912
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2759 - loss: 2.1912
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1912
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1912 - val_accuracy: 0.3490 - val_loss: 2.1194
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 23ms/step - accuracy: 0.3125 - loss: 1.8666
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2154 - loss: 2.2207  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2316 - loss: 2.2354
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2446 - loss: 2.2249
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2181
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2141
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2586 - loss: 2.2107
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2083
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2057
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2644 - loss: 2.2032
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2659 - loss: 2.2004
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.1979
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2682 - loss: 2.1959
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.1943
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2700 - loss: 2.1936
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1931
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2711 - loss: 2.1930
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.1931
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2718 - loss: 2.1931
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2721 - loss: 2.1934
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2723 - loss: 2.1935
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1935
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1934
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2728 - loss: 2.1934
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2728 - loss: 2.1933
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 2.1931
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 2.1929
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1925
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2731 - loss: 2.1922
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2732 - loss: 2.1918
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2734 - loss: 2.1914
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2735 - loss: 2.1909
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2736 - loss: 2.1906
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.1902
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.1898
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2738 - loss: 2.1895
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2739 - loss: 2.1891
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2739 - loss: 2.1888
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.1885
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.1882
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.1880
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1877
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1874
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1874 - val_accuracy: 0.3403 - val_loss: 2.0928
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.8763
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2953 - loss: 2.0809  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2942 - loss: 2.0969
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1123
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1270
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1375
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2754 - loss: 2.1438
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2731 - loss: 2.1479
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2717 - loss: 2.1502
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2709 - loss: 2.1521
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2701 - loss: 2.1543
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.1563
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2687 - loss: 2.1575
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2683 - loss: 2.1584
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.1594
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.1602
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.1611
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.1618
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.1621
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2677 - loss: 2.1625
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2678 - loss: 2.1627
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2680 - loss: 2.1630
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2682 - loss: 2.1631
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2685 - loss: 2.1631
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2687 - loss: 2.1632
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2689 - loss: 2.1633
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2691 - loss: 2.1632
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2693 - loss: 2.1631
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.1630
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.1629
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.1628
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2701 - loss: 2.1628
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2703 - loss: 2.1627
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.1627
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2706 - loss: 2.1626
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.1625
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1624
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.1624
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2709 - loss: 2.1623
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.1622
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2711 - loss: 2.1620
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2712 - loss: 2.1618
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.1616
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2714 - loss: 2.1616 - val_accuracy: 0.3524 - val_loss: 2.0719
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.2738
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2436 - loss: 2.1152  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2574 - loss: 2.1237
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2611 - loss: 2.1297
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2646 - loss: 2.1327
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.1309
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.1295
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2738 - loss: 2.1281
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2755 - loss: 2.1283
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1293
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2775 - loss: 2.1298
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1298
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1300
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1304
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1306
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1307
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1307
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1307
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1306
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1304
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1301
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1298
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1295
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1293
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1291
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1290
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1289
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1289
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1288
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1288
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1288
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1288
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1289
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1290
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1290
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1291
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1290
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1290
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1289
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1289
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1288
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1288
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1288 - val_accuracy: 0.3272 - val_loss: 2.0998
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3296
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3322 - loss: 2.0191  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0189
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0276
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0362
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0430
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0490
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0543
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3083 - loss: 2.0577
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 2.0608
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3067 - loss: 2.0626
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0641
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0649
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0662
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0674
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0683
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0692
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0702
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0713
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0726
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0737
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0748
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0758
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0767
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0775
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0783
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0791
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0799
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0807
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0815
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0821
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0827
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0831
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0837
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 2.0843
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0849
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0855
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0861
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.0867
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0872
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0878
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0883
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.0888
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 2.0893
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0893 - val_accuracy: 0.3524 - val_loss: 2.0660
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.2769
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1338  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1104
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0943
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0906
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0908
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0921
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 2.0951
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0965
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.0970
[1m 285/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0980
[1m 312/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 2.0985
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.0983
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0980
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.0975
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0971
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.0968
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.0968
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.0968
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0968
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0967
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 2.0966
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3010 - loss: 2.0967
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.0968
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0968
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0967
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0967
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0967
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0967
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0967
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0967
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0967
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0967
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0968
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0968
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0969
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0970
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0969
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0969
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0968
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0968
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0967
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0967
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0967 - val_accuracy: 0.3248 - val_loss: 2.1253
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9113
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2921 - loss: 2.0652  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2914 - loss: 2.0768
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2891 - loss: 2.0830
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2889 - loss: 2.0822
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2895 - loss: 2.0819
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 2.0799
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.0769
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 2.0751
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 2.0738
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.0734
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 2.0734
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 2.0733
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 2.0731
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0728
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.0726
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0724
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3015 - loss: 2.0722
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3015 - loss: 2.0723
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0725
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0728
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0731
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0735
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0736
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0739
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0740
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0741
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0742
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 2.0743
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3019 - loss: 2.0744
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0744
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0744
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0744
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0744
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0744
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0744
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0745
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0745
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0745
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0745
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0745
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3033 - loss: 2.0745
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0744
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0744
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0744 - val_accuracy: 0.3389 - val_loss: 2.0685
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0932
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0405  
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0459
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0465
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0477
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0482
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0497
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0515
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0525
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0530
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0534
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3033 - loss: 2.0538
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0543
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0546
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.0548
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0552
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0555
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0561
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0566
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0568
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0572
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0573
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0574
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0575
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0577
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0577
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0576
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0576
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0575
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0575
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0576
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0576
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0575
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0575
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0574
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3072 - loss: 2.0575
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3073 - loss: 2.0574
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3073 - loss: 2.0574
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3074 - loss: 2.0575
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0575
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0574
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3076 - loss: 2.0573
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0572
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3078 - loss: 2.0571
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3078 - loss: 2.0570 - val_accuracy: 0.3339 - val_loss: 2.0980
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1105
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0249  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0551
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3088 - loss: 2.0510
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0473
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0433
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3162 - loss: 2.0420
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0412
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0406
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 2.0412
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 2.0422
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 2.0435
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0448
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0462
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0470
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0478
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 2.0484
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0488
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 2.0489
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0488
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0485
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0482
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0480
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0479
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0479
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0478
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0479
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0479
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0480
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0480
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0479
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0479
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0479
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0479
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0479
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0479
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0479
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0479
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0479
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0478
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0477
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0477
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0477
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0476
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0476 - val_accuracy: 0.3317 - val_loss: 2.0996
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9533
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3315 - loss: 1.9939  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3328 - loss: 1.9916
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3342 - loss: 1.9940
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 2.0013
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 2.0056
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0082
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3301 - loss: 2.0096
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 2.0121
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3279 - loss: 2.0150
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0178
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0197
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3255 - loss: 2.0208
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0218
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0230
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0237
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0244
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0254
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0265
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0276
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0287
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0295
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0303
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0311
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0319
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0323
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0325
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0328
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0330
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0331
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0333
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0335
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0336
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0337
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0337
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0338
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0338
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0338
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0338
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0338
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0338
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0338
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0339
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0339 - val_accuracy: 0.3234 - val_loss: 2.0819

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 637ms/step
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 992us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:09[0m 848ms/step
[1m 45/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m 97/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m153/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 996us/step
[1m204/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 994us/step
[1m256/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 989us/step
[1m306/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 993us/step
[1m354/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m405/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 1ms/step
[1m459/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 992us/step
[1m505/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 1ms/step  
[1m554/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 1ms/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 963us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 52/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 996us/step
[1m105/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 971us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 36.49 [%]
Global F1 score (validation) = 34.26 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.01485018 0.00801291 0.01208614 ... 0.04108673 0.03114066 0.01305115]
 [0.00188666 0.00086365 0.00218796 ... 0.11162613 0.0063912  0.00284392]
 [0.00152082 0.00209485 0.00255546 ... 0.00399855 0.00261273 0.00089464]
 ...
 [0.17234053 0.03737271 0.14606811 ... 0.00446669 0.1841431  0.15808891]
 [0.19008054 0.04579759 0.15270945 ... 0.00660926 0.14212789 0.13445629]
 [0.16987395 0.09632616 0.10529429 ... 0.01896278 0.10071409 0.05326389]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 40.75 [%]
Global accuracy score (test) = 29.27 [%]
Global F1 score (train) = 39.34 [%]
Global F1 score (test) = 27.69 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.28      0.41      0.33       184
 CAMINAR CON MÓVIL O LIBRO       0.16      0.16      0.16       184
       CAMINAR USUAL SPEED       0.09      0.03      0.05       184
            CAMINAR ZIGZAG       0.28      0.37      0.32       184
          DE PIE BARRIENDO       0.57      0.32      0.41       184
   DE PIE DOBLANDO TOALLAS       0.28      0.32      0.30       184
    DE PIE MOVIENDO LIBROS       0.19      0.18      0.19       184
          DE PIE USANDO PC       0.18      0.15      0.17       184
        FASE REPOSO CON K5       0.33      0.73      0.45       184
INCREMENTAL CICLOERGOMETRO       0.44      0.51      0.47       184
           SENTADO LEYENDO       0.30      0.17      0.22       184
         SENTADO USANDO PC       0.27      0.09      0.13       184
      SENTADO VIENDO LA TV       0.21      0.23      0.22       184
   SUBIR Y BAJAR ESCALERAS       0.25      0.23      0.24       184
                    TROTAR       0.50      0.50      0.50       161

                  accuracy                           0.29      2737
                 macro avg       0.29      0.29      0.28      2737
              weighted avg       0.29      0.29      0.28      2737


Accuracy capturado en la ejecución 20: 29.27 [%]
F1-score capturado en la ejecución 20: 27.69 [%]

=== EJECUCIÓN 21 ===

--- TRAIN (ejecución 21) ---

--- TEST (ejecución 21) ---
2025-11-07 13:22:22.614581: 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`.
2025-11-07 13:22:22.626066: 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 00:00:1762518142.640067 2815676 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762518142.644254 2815676 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762518142.654578 2815676 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518142.654601 2815676 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518142.654603 2815676 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518142.654605 2815676 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:22:22.657713: 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 00:00:1762518144.926280 2815676 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762518147.963320 2815807 service.cc:152] XLA service 0x7f8108014480 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762518147.963373 2815807 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:22:28.036246: 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 00:00:1762518148.487077 2815807 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762518151.019029 2815807 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43:50[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.9173
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0467 - loss: 3.4474        
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0537 - loss: 3.4082
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0593 - loss: 3.3843
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0616 - loss: 3.3667
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0631 - loss: 3.3528
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0647 - loss: 3.3415
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0660 - loss: 3.3329
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0672 - loss: 3.3228
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0683 - loss: 3.3139
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0693 - loss: 3.3057
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0706 - loss: 3.2966
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0719 - loss: 3.2878
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0730 - loss: 3.2806
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0742 - loss: 3.2719
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0752 - loss: 3.2647
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0763 - loss: 3.2578
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0774 - loss: 3.2511
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0786 - loss: 3.2439
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0798 - loss: 3.2369
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0809 - loss: 3.2305
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0823 - loss: 3.2231
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0838 - loss: 3.2148
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0850 - loss: 3.2081
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0863 - loss: 3.2012
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0876 - loss: 3.1945
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0888 - loss: 3.1882
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0899 - loss: 3.1824
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0910 - loss: 3.1768
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0921 - loss: 3.1710
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0932 - loss: 3.1654
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0941 - loss: 3.1602
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0952 - loss: 3.1547
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0963 - loss: 3.1492
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0972 - loss: 3.1443
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0981 - loss: 3.1396
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0991 - loss: 3.1341
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1000 - loss: 3.1293
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1009 - loss: 3.1245
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1018 - loss: 3.1196
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1027 - loss: 3.1150
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1035 - loss: 3.1105
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1044 - loss: 3.1057
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1051 - loss: 3.1018
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1051 - loss: 3.1017 - val_accuracy: 0.2482 - val_loss: 2.3552
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.4683
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1890 - loss: 2.5428  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1738 - loss: 2.5963
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1704 - loss: 2.6195
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1695 - loss: 2.6356
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1687 - loss: 2.6450
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1686 - loss: 2.6503
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1695 - loss: 2.6525
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1703 - loss: 2.6538
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1712 - loss: 2.6533
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1721 - loss: 2.6519
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1730 - loss: 2.6501
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1739 - loss: 2.6481
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1746 - loss: 2.6468
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1752 - loss: 2.6456
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1756 - loss: 2.6446
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1759 - loss: 2.6438
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1762 - loss: 2.6430
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1765 - loss: 2.6421
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1769 - loss: 2.6411
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1772 - loss: 2.6401
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1775 - loss: 2.6390
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1777 - loss: 2.6381
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6372
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1782 - loss: 2.6363
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1785 - loss: 2.6355
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1787 - loss: 2.6346
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1789 - loss: 2.6338
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1791 - loss: 2.6331
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.6324
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6317
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6310
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1799 - loss: 2.6303
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1801 - loss: 2.6296
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.6288
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6281
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1806 - loss: 2.6274
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1808 - loss: 2.6267
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1810 - loss: 2.6261
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1811 - loss: 2.6255
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1813 - loss: 2.6249
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1814 - loss: 2.6242
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1816 - loss: 2.6236
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1817 - loss: 2.6231 - val_accuracy: 0.2730 - val_loss: 2.2605
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0838
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1934 - loss: 2.5896  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1954 - loss: 2.5675
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1987 - loss: 2.5536
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2007 - loss: 2.5414
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2015 - loss: 2.5355
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2019 - loss: 2.5318
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2029 - loss: 2.5287
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2034 - loss: 2.5270
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2038 - loss: 2.5257
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2042 - loss: 2.5244
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2043 - loss: 2.5237
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2043 - loss: 2.5233
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2044 - loss: 2.5225
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.5221
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.5216
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.5210
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2047 - loss: 2.5198
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2048 - loss: 2.5188
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2048 - loss: 2.5178
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2049 - loss: 2.5168
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2051 - loss: 2.5159
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2052 - loss: 2.5153
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2053 - loss: 2.5146
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2053 - loss: 2.5140
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2053 - loss: 2.5135
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2054 - loss: 2.5129
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2054 - loss: 2.5123
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2055 - loss: 2.5117
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2055 - loss: 2.5111
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2056 - loss: 2.5105
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2056 - loss: 2.5098
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.5093
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2057 - loss: 2.5086
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2058 - loss: 2.5080
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2058 - loss: 2.5074
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2059 - loss: 2.5068
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2059 - loss: 2.5064
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2059 - loss: 2.5059
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2060 - loss: 2.5054
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2060 - loss: 2.5049
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2060 - loss: 2.5043
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2061 - loss: 2.5038
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2061 - loss: 2.5034
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2061 - loss: 2.5031 - val_accuracy: 0.2837 - val_loss: 2.2145
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.4375 - loss: 2.2230
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2875 - loss: 2.2342  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2541 - loss: 2.3095
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3395
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2379 - loss: 2.3555
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2345 - loss: 2.3648
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2315 - loss: 2.3723
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2300 - loss: 2.3762
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3787
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2284 - loss: 2.3803
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2278 - loss: 2.3824
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2274 - loss: 2.3846
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3864
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.3883
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2263 - loss: 2.3897
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2259 - loss: 2.3912
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2256 - loss: 2.3927
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3937
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.3948
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2251 - loss: 2.3957
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2251 - loss: 2.3965
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2251 - loss: 2.3969
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2252 - loss: 2.3972
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2252 - loss: 2.3974
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2252 - loss: 2.3978
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2252 - loss: 2.3982
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2253 - loss: 2.3984
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2253 - loss: 2.3986
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3988
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3989
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3990
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3990
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3990
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3990
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3989
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3989
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3989
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3989
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3990
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3990
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3991
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3991
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3992
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3992 - val_accuracy: 0.2956 - val_loss: 2.1805
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2135
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2522  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2593
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2500 - loss: 2.2810
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2474 - loss: 2.2923
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.3001
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2447 - loss: 2.3071
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2439 - loss: 2.3117
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3154
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2414 - loss: 2.3183
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2403 - loss: 2.3208
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2393 - loss: 2.3229
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2383 - loss: 2.3251
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2375 - loss: 2.3265
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2367 - loss: 2.3278
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2360 - loss: 2.3288
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3293
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2352 - loss: 2.3297
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3303
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3306
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3308
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3312
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3316
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3318
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3318
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3319
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3320
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3321
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3323
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3324
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3326
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3327
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3328
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3328
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3329
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3329
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3330
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3331
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3331
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3332
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3333
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3333
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3333
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3333
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2345 - loss: 2.3333 - val_accuracy: 0.3103 - val_loss: 2.1462
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2500 - loss: 2.1217
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2529 - loss: 2.2777  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2520 - loss: 2.2875
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2496 - loss: 2.3014
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2480 - loss: 2.3103
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2483 - loss: 2.3139
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.3155
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2491 - loss: 2.3157
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2493 - loss: 2.3149
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2493 - loss: 2.3143
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2494 - loss: 2.3133
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.3124
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2501 - loss: 2.3115
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2505 - loss: 2.3108
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.3104
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2508 - loss: 2.3099
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2509 - loss: 2.3096
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2509 - loss: 2.3093
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.3089
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.3086
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.3082
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.3078
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2511 - loss: 2.3074
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2511 - loss: 2.3071
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2510 - loss: 2.3068
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2510 - loss: 2.3066
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.3064
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2508 - loss: 2.3062
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2507 - loss: 2.3062
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2506 - loss: 2.3063
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.3063
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2504 - loss: 2.3063
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2503 - loss: 2.3062
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2503 - loss: 2.3062
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2502 - loss: 2.3060
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2502 - loss: 2.3059
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2501 - loss: 2.3058
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2501 - loss: 2.3056
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2500 - loss: 2.3054
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2500 - loss: 2.3053
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2499 - loss: 2.3052
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2499 - loss: 2.3051
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2498 - loss: 2.3050
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2497 - loss: 2.3049
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2497 - loss: 2.3049 - val_accuracy: 0.3159 - val_loss: 2.1168
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.0625 - loss: 2.4316
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2048 - loss: 2.3131  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2348 - loss: 2.2587
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2418 - loss: 2.2544
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2576
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2426 - loss: 2.2601
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2423 - loss: 2.2612
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2423 - loss: 2.2628
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2637
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2649
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2437 - loss: 2.2653
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2441 - loss: 2.2659
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2445 - loss: 2.2666
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2448 - loss: 2.2671
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2452 - loss: 2.2677
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2679
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2459 - loss: 2.2680
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2678
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2675
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2670
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2474 - loss: 2.2667
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2476 - loss: 2.2663
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.2659
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2482 - loss: 2.2655
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2652
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2489 - loss: 2.2648
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2647
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2494 - loss: 2.2645
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2497 - loss: 2.2644
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2642
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2501 - loss: 2.2641
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2503 - loss: 2.2639
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.2637
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2506 - loss: 2.2636
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2635
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2634
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2633
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2632
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2631
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2630
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2515 - loss: 2.2628
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2516 - loss: 2.2627
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2517 - loss: 2.2626
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2518 - loss: 2.2626 - val_accuracy: 0.3206 - val_loss: 2.1013
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.3849
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 3ms/step - accuracy: 0.2916 - loss: 2.2613  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2810 - loss: 2.2273
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2742 - loss: 2.2267
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2702 - loss: 2.2287
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2680 - loss: 2.2296
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2668 - loss: 2.2285
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2657 - loss: 2.2285
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2644 - loss: 2.2285
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2285
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2287
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2293
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2295
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2296
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2299
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2300
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2302
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2306
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2308
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2308
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2306
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2306
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2305
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2304
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2304
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2303
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2304
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2303
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2302
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2300
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2298
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2296
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2294
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2293
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2292
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2291
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2290
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2290
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2290
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2290
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2291
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2291
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2292 - val_accuracy: 0.3204 - val_loss: 2.1171
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.1875 - loss: 2.2174
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2483 - loss: 2.2791  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2521 - loss: 2.2663
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2618
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2550
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2496
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2471
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2450
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.2415
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2378
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2653 - loss: 2.2344
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2663 - loss: 2.2321
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2669 - loss: 2.2304
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.2293
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2677 - loss: 2.2280
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2682 - loss: 2.2265
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2689 - loss: 2.2248
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2234
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2700 - loss: 2.2221
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.2208
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2709 - loss: 2.2196
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2713 - loss: 2.2186
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.2176
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.2167
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2721 - loss: 2.2159
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2724 - loss: 2.2150
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.2140
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2728 - loss: 2.2131
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2731 - loss: 2.2123
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2732 - loss: 2.2116
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2734 - loss: 2.2111
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2734 - loss: 2.2106
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2735 - loss: 2.2101
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2736 - loss: 2.2096
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2736 - loss: 2.2091
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.2087
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.2084
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.2080
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.2076
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.2072
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2738 - loss: 2.2068
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2738 - loss: 2.2063
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2738 - loss: 2.2059 - val_accuracy: 0.3562 - val_loss: 2.0850
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2268
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3035 - loss: 2.1514  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1563
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1701
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1763
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1772
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1789
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1805
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1818
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1825
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1830
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1832
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1829
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1823
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1819
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1818
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1817
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1814
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1811
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1808
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1806
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1802
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1797
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1793
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1789
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1786
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2786 - loss: 2.1784
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1782
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2782 - loss: 2.1780
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2781 - loss: 2.1778
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2780 - loss: 2.1775
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1772
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1769
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1766
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1763
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1760
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1757
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1754
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1752
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1750
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1747
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1746
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1744
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1743
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1741 - val_accuracy: 0.3300 - val_loss: 2.0865
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2714
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1254  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2960 - loss: 2.1238
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1273
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2910 - loss: 2.1250
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1251
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1247
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1258
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1273
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1297
[1m 265/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1317
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1329
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1338
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1344
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1347
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1349
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1349
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1353
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1355
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1356
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1355
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1355
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1355
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1357
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1357
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1357
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1357
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1357
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1358
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1357
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1357
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1356
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1356
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1356
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1356
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1355
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1355
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1355
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1355
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1356
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1356
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1357
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1358
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1359
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1360 - val_accuracy: 0.3329 - val_loss: 2.0766
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 1.9504
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0720  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0775
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3186 - loss: 2.0820
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0898
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0930
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0957
[1m 179/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0979
[1m 205/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.1008
[1m 230/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3093 - loss: 2.1036
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 2.1059
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3075 - loss: 2.1083
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3065 - loss: 2.1111
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 2.1131
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.1146
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 2.1158
[1m 417/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 2.1171
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.1183
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1196
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1204
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1212
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1216
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1219
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1220
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2993 - loss: 2.1221
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 2.1223
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1224
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2988 - loss: 2.1224
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1224
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1223
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1223
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 2.1221
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 2.1220
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 2.1219
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1217
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1215
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1212
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2988 - loss: 2.1210
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1208
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1206
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 2.1204
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 2.1203
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 2.1201
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1200
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1200 - val_accuracy: 0.3621 - val_loss: 2.0567
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4470
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2565  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1772
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2936 - loss: 2.1478
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2955 - loss: 2.1360
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 2.1293
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1212
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1152
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1106
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1079
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.1057
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1048
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1045
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1040
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1035
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1030
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1025
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1020
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1019
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1018
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1018
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1017
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1014
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1012
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1010
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1009
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1009
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3000 - loss: 2.1008
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1007
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1006
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1006
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1006
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1005
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1004
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1003
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1002
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1002
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1001
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1000
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1000
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.0999
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.0999
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.0999
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.0999
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2996 - loss: 2.0998 - val_accuracy: 0.3540 - val_loss: 2.1119
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9918
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1103  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2899 - loss: 2.1149
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1089
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1042
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2988 - loss: 2.1026
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1008
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1011
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.1009
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1007
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.1002
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0996
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0986
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0976
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0969
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0963
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0959
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0955
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0954
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0955
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3018 - loss: 2.0957
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0958
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0958
[1m 625/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0958
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 2.0958
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3009 - loss: 2.0958
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0959
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0959
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3007 - loss: 2.0960
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0960
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0959
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0959
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0958
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0957
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0956
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0955
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0955
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0955
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0955
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0954
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0954
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0953
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0953
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0953 - val_accuracy: 0.3315 - val_loss: 2.0774
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.4236
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1578  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1532
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 2.1452
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 2.1358
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.1256
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 2.1191
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.1126
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.1082
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3120 - loss: 2.1050
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 2.1024
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0992
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0970
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0950
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0929
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0912
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0894
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0881
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0869
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0857
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0847
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0837
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0827
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0818
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0810
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0803
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0797
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0791
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0787
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0783
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0779
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0775
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0770
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0766
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0761
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0758
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0755
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0751
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0748
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0745
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0741
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0738
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0736
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0734
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0733 - val_accuracy: 0.3397 - val_loss: 2.0493
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 23ms/step - accuracy: 0.3750 - loss: 1.7268
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0426  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0405
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0419
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0453
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0482
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0504
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0512
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0525
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0539
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0548
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3160 - loss: 2.0557
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0565
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0568
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0567
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0566
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0563
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0559
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0556
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0553
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0552
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0550
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0548
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0545
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0542
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0540
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0539
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0538
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0539
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0539
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0539
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0539
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0539
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0539
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0538
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0538
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0538
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0539
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0540
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0541
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0541
[1m1103/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0542
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0543
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0544
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0544 - val_accuracy: 0.3357 - val_loss: 2.0863
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.5000 - loss: 1.7893
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3547 - loss: 2.0320  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3494 - loss: 2.0258
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3415 - loss: 2.0342
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3355 - loss: 2.0420
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3310 - loss: 2.0450
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 2.0459
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0455
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0450
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 2.0454
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0457
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0456
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3232 - loss: 2.0451
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0446
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0441
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0433
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0425
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0419
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0412
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3215 - loss: 2.0407
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0403
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0400
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3209 - loss: 2.0398
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0397
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0396
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0395
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0395
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0393
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0391
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0388
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0385
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0383
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0380
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0377
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0375
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0372
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0370
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0368
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0367
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0365
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0363
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0362
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0360
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0360 - val_accuracy: 0.3504 - val_loss: 2.0987
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.6919
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3479 - loss: 2.0104  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3410 - loss: 1.9978
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3344 - loss: 2.0084
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 2.0147
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3269 - loss: 2.0193
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0220
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0233
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0240
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0240
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0242
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0242
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0242
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0242
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0244
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0247
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0247
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0245
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0244
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0245
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0245
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0247
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0248
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0249
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0250
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0250
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0250
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0250
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0250
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0248
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0247
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0245
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0243
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0242
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0240
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0238
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0236
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0235
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0233
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0233
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0232
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0230
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0229
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0229 - val_accuracy: 0.3613 - val_loss: 2.0849
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9466
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3394 - loss: 1.9796  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3323 - loss: 1.9975
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3282 - loss: 2.0061
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0152
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3255 - loss: 2.0197
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0225
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0240
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0252
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0259
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3243 - loss: 2.0257
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0244
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3255 - loss: 2.0231
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0221
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0214
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0208
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0201
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3278 - loss: 2.0194
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3282 - loss: 2.0186
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 2.0180
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3288 - loss: 2.0172
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 2.0164
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 2.0157
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 2.0151
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 2.0144
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0140
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0135
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0131
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3309 - loss: 2.0128
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 2.0126
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0125
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3312 - loss: 2.0124
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3313 - loss: 2.0124
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3313 - loss: 2.0124
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3314 - loss: 2.0124
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3314 - loss: 2.0124
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 2.0124
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 2.0123
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 2.0122
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3315 - loss: 2.0121
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0119
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0118
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3317 - loss: 2.0117
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3317 - loss: 2.0116 - val_accuracy: 0.3498 - val_loss: 2.0843
Epoch 20/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1580
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3469 - loss: 1.9426  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3423 - loss: 1.9582
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3364 - loss: 1.9650
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3350 - loss: 1.9631
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3341 - loss: 1.9622
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3337 - loss: 1.9618
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9621
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.9627
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 1.9635
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9646
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 1.9657
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3332 - loss: 1.9668
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 1.9680
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3328 - loss: 1.9689
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 1.9696
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.9705
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.9712
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.9718
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.9724
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3325 - loss: 1.9730
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3326 - loss: 1.9732
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 1.9734
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3329 - loss: 1.9735
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3331 - loss: 1.9735
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3333 - loss: 1.9735
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3334 - loss: 1.9736
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3334 - loss: 1.9738
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.9740
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.9743
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.9746
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.9748
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.9751
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9753
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9756
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9760
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9764
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9767
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9770
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9774
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3336 - loss: 1.9776
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.9779
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3335 - loss: 1.9782
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3335 - loss: 1.9785 - val_accuracy: 0.3367 - val_loss: 2.0911

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 646ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 975us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:01[0m 835ms/step
[1m 49/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m104/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 983us/step
[1m160/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 955us/step
[1m218/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 934us/step
[1m274/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 927us/step
[1m331/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 920us/step
[1m381/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 933us/step
[1m432/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 939us/step
[1m485/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 941us/step
[1m544/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 931us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 992us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 46/158[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m 99/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step
[1m149/158[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 1ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 32.34 [%]
Global F1 score (validation) = 29.83 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.0385802  0.01508748 0.01503892 ... 0.0186522  0.04240478 0.01580016]
 [0.00185847 0.00209001 0.00189499 ... 0.1208007  0.00600731 0.00370696]
 [0.00067974 0.00054378 0.00076844 ... 0.01023926 0.0006741  0.00074974]
 ...
 [0.3668798  0.02963656 0.09001158 ... 0.00738106 0.11284643 0.09086306]
 [0.24584794 0.0600832  0.08348463 ... 0.01370638 0.08705973 0.06874692]
 [0.12809476 0.0702211  0.19629823 ... 0.00214236 0.24565051 0.07044927]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 38.37 [%]
Global accuracy score (test) = 26.89 [%]
Global F1 score (train) = 36.48 [%]
Global F1 score (test) = 24.85 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.22      0.69      0.34       184
 CAMINAR CON MÓVIL O LIBRO       0.17      0.20      0.18       184
       CAMINAR USUAL SPEED       0.21      0.04      0.07       184
            CAMINAR ZIGZAG       0.08      0.01      0.02       184
          DE PIE BARRIENDO       0.47      0.21      0.29       184
   DE PIE DOBLANDO TOALLAS       0.27      0.35      0.31       184
    DE PIE MOVIENDO LIBROS       0.20      0.16      0.18       184
          DE PIE USANDO PC       0.15      0.20      0.17       184
        FASE REPOSO CON K5       0.33      0.60      0.42       184
INCREMENTAL CICLOERGOMETRO       0.54      0.40      0.46       184
           SENTADO LEYENDO       0.09      0.05      0.06       184
         SENTADO USANDO PC       0.23      0.07      0.11       184
      SENTADO VIENDO LA TV       0.17      0.21      0.18       184
   SUBIR Y BAJAR ESCALERAS       0.34      0.36      0.35       184
                    TROTAR       0.67      0.52      0.59       161

                  accuracy                           0.27      2737
                 macro avg       0.28      0.27      0.25      2737
              weighted avg       0.27      0.27      0.25      2737


Accuracy capturado en la ejecución 21: 26.89 [%]
F1-score capturado en la ejecución 21: 24.85 [%]

=== EJECUCIÓN 22 ===

--- TRAIN (ejecución 22) ---

--- TEST (ejecución 22) ---
2025-11-07 13:23:39.689623: 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`.
2025-11-07 13:23:39.700864: 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 00:00:1762518219.714042 2818973 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762518219.718202 2818973 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762518219.727989 2818973 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518219.728007 2818973 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518219.728017 2818973 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518219.728018 2818973 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:23:39.731246: 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 00:00:1762518221.985479 2818973 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762518225.108593 2819106 service.cc:152] XLA service 0x7c19ec003550 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762518225.108639 2819106 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:23:45.188969: 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 00:00:1762518225.633162 2819106 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762518228.173697 2819106 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45:44[0m 5s/step - accuracy: 0.1250 - loss: 3.3010
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0745 - loss: 3.5536    
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0680 - loss: 3.5599
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0693 - loss: 3.5372
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0710 - loss: 3.5105
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0724 - loss: 3.4879
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0740 - loss: 3.4694
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0758 - loss: 3.4517
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0774 - loss: 3.4366
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0790 - loss: 3.4218
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0803 - loss: 3.4087
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0814 - loss: 3.3981
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0826 - loss: 3.3869
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0837 - loss: 3.3765
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0850 - loss: 3.3663
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0863 - loss: 3.3564
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0874 - loss: 3.3475
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0883 - loss: 3.3398
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0894 - loss: 3.3316
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0904 - loss: 3.3238
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0912 - loss: 3.3170
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0922 - loss: 3.3095
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0932 - loss: 3.3023
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0942 - loss: 3.2950
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0951 - loss: 3.2881
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0960 - loss: 3.2811
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0969 - loss: 3.2746
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0977 - loss: 3.2684
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0985 - loss: 3.2624
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0993 - loss: 3.2562
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1001 - loss: 3.2498
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1009 - loss: 3.2435
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1016 - loss: 3.2380
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1024 - loss: 3.2319
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1032 - loss: 3.2260
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1039 - loss: 3.2202
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1046 - loss: 3.2149
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1053 - loss: 3.2096
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1060 - loss: 3.2040
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1067 - loss: 3.1987
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1073 - loss: 3.1945
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1080 - loss: 3.1894
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1086 - loss: 3.1849
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1091 - loss: 3.1812
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1091 - loss: 3.1810 - val_accuracy: 0.2317 - val_loss: 2.3467
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2500 - loss: 2.9681
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1705 - loss: 2.8046  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1714 - loss: 2.7810
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1711 - loss: 2.7610
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1711 - loss: 2.7493
[1m 129/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1722 - loss: 2.7385
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1731 - loss: 2.7306
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1740 - loss: 2.7243
[1m 206/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1745 - loss: 2.7200
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1749 - loss: 2.7174
[1m 254/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1755 - loss: 2.7146
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1761 - loss: 2.7116
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1768 - loss: 2.7086
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1773 - loss: 2.7063
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1777 - loss: 2.7043
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1781 - loss: 2.7024
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.7004
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1788 - loss: 2.6984
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1792 - loss: 2.6960
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6941
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1799 - loss: 2.6920
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1802 - loss: 2.6900
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6882
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1806 - loss: 2.6864
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1808 - loss: 2.6849
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1810 - loss: 2.6835
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1812 - loss: 2.6819
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1813 - loss: 2.6807
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1815 - loss: 2.6793
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1816 - loss: 2.6780
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1818 - loss: 2.6767
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1819 - loss: 2.6753
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1820 - loss: 2.6742
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1822 - loss: 2.6729
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6718
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1824 - loss: 2.6706
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1825 - loss: 2.6695
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6683
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6671
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.6659
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1829 - loss: 2.6647
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1830 - loss: 2.6636
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1831 - loss: 2.6626
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.6616
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1833 - loss: 2.6606
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1834 - loss: 2.6598 - val_accuracy: 0.2738 - val_loss: 2.2315
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.6270
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1921 - loss: 2.5606  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1914 - loss: 2.5457
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1889 - loss: 2.5469
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1881 - loss: 2.5434
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1875 - loss: 2.5418
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1872 - loss: 2.5395
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1880 - loss: 2.5364
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1894 - loss: 2.5327
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1907 - loss: 2.5288
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1918 - loss: 2.5250
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1926 - loss: 2.5223
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1931 - loss: 2.5201
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1937 - loss: 2.5180
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1942 - loss: 2.5168
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1946 - loss: 2.5155
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1950 - loss: 2.5144
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1955 - loss: 2.5135
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1961 - loss: 2.5122
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1965 - loss: 2.5111
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1968 - loss: 2.5101
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1971 - loss: 2.5091
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1973 - loss: 2.5083
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1974 - loss: 2.5076
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1975 - loss: 2.5070
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1975 - loss: 2.5063
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1976 - loss: 2.5056
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1977 - loss: 2.5050
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1977 - loss: 2.5043
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1978 - loss: 2.5036
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1979 - loss: 2.5029
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1980 - loss: 2.5023
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1981 - loss: 2.5018
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1981 - loss: 2.5013
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1982 - loss: 2.5008
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1982 - loss: 2.5004
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.5000
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.4995
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.4991
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1984 - loss: 2.4986
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1985 - loss: 2.4981
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1986 - loss: 2.4976
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1987 - loss: 2.4972
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1988 - loss: 2.4967
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1988 - loss: 2.4966 - val_accuracy: 0.2770 - val_loss: 2.1969
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.6228
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1957 - loss: 2.4785  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2091 - loss: 2.4306
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2167 - loss: 2.4096
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2200 - loss: 2.4017
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2208 - loss: 2.3997
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2209 - loss: 2.4002
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2206 - loss: 2.4013
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2205 - loss: 2.4020
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2203 - loss: 2.4032
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2205 - loss: 2.4034
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2210 - loss: 2.4029
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2214 - loss: 2.4028
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2218 - loss: 2.4024
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2221 - loss: 2.4019
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2224 - loss: 2.4013
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2226 - loss: 2.4012
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2229 - loss: 2.4011
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2231 - loss: 2.4011
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2231 - loss: 2.4011
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2232 - loss: 2.4010
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2233 - loss: 2.4007
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2234 - loss: 2.4004
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2234 - loss: 2.4001
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2234 - loss: 2.4001
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2234 - loss: 2.4000
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2234 - loss: 2.3999
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2233 - loss: 2.3999
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2232 - loss: 2.3999
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2232 - loss: 2.3999
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2231 - loss: 2.3999
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2230 - loss: 2.4000
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2230 - loss: 2.4001
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2230 - loss: 2.4001
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.4002
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.4002
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.4002
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2229 - loss: 2.4001
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.4001
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.4000
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.4000
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.3999
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.3998
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2228 - loss: 2.3997
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2227 - loss: 2.3997 - val_accuracy: 0.2867 - val_loss: 2.1806
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2564
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3329  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2365 - loss: 2.3474
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3658
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2281 - loss: 2.3684
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3685
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2277 - loss: 2.3685
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2273 - loss: 2.3678
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2272 - loss: 2.3676
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2274 - loss: 2.3663
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2275 - loss: 2.3653
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2276 - loss: 2.3644
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2277 - loss: 2.3636
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2276 - loss: 2.3628
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2275 - loss: 2.3619
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2275 - loss: 2.3613
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2274 - loss: 2.3607
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2272 - loss: 2.3602
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2271 - loss: 2.3596
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2271 - loss: 2.3592
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3586
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3581
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2269 - loss: 2.3576
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2269 - loss: 2.3569
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2269 - loss: 2.3563
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3557
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3551
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2270 - loss: 2.3546
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2271 - loss: 2.3541
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2272 - loss: 2.3535
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2273 - loss: 2.3531
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2274 - loss: 2.3526
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2275 - loss: 2.3522
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2276 - loss: 2.3517
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2277 - loss: 2.3513
[1m 954/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2278 - loss: 2.3509
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3506
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3502
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2281 - loss: 2.3499
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2282 - loss: 2.3495
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2283 - loss: 2.3492
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2284 - loss: 2.3488
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2285 - loss: 2.3485
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3482 - val_accuracy: 0.3012 - val_loss: 2.1564
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.9868
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2676 - loss: 2.3423  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2547 - loss: 2.3503
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2531 - loss: 2.3396
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2515 - loss: 2.3292
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2515 - loss: 2.3206
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2512 - loss: 2.3168
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2504 - loss: 2.3133
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.3105
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.3089
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.3079
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2483 - loss: 2.3068
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2481 - loss: 2.3058
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.3048
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2477 - loss: 2.3041
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2476 - loss: 2.3036
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2475 - loss: 2.3031
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2474 - loss: 2.3025
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2474 - loss: 2.3019
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2473 - loss: 2.3013
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2472 - loss: 2.3009
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2471 - loss: 2.3005
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2469 - loss: 2.3001
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2468 - loss: 2.2996
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2993
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2466 - loss: 2.2989
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.2984
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2464 - loss: 2.2981
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2978
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2974
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2971
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.2967
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2460 - loss: 2.2964
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2459 - loss: 2.2960
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2458 - loss: 2.2957
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2457 - loss: 2.2953
[1m 947/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2457 - loss: 2.2950
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2456 - loss: 2.2945
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2456 - loss: 2.2941
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2937
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2933
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2930
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2926
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2923
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2919 - val_accuracy: 0.3115 - val_loss: 2.1158
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 1.9473
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2528 - loss: 2.2121  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2476 - loss: 2.2504
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2526
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2520 - loss: 2.2562
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2528 - loss: 2.2557
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2538
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2527
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2529
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2527
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2524
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2526
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2532
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2540
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2550
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2536 - loss: 2.2555
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2533 - loss: 2.2560
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2530 - loss: 2.2564
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2528 - loss: 2.2567
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2525 - loss: 2.2571
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2523 - loss: 2.2575
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2520 - loss: 2.2579
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2518 - loss: 2.2581
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2517 - loss: 2.2583
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2516 - loss: 2.2585
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2514 - loss: 2.2587
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2588
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2589
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2590
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2589
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2588
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2587
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2586
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2585
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2584
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2583
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2581
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2580
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2578
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2576
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2574
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2572
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2570
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2514 - loss: 2.2567
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2514 - loss: 2.2566 - val_accuracy: 0.3192 - val_loss: 2.1319
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 1.6934
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3133 - loss: 2.1087  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1569
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1729
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1798
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1850
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2895 - loss: 2.1890
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1914
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1933
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1944
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1955
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1965
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1972
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1979
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1987
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1997
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2782 - loss: 2.2005
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2778 - loss: 2.2011
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2774 - loss: 2.2019
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.2026
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2766 - loss: 2.2032
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2761 - loss: 2.2040
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 2.2047
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2752 - loss: 2.2053
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2747 - loss: 2.2059
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2744 - loss: 2.2063
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2067
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2737 - loss: 2.2069
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2733 - loss: 2.2073
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2730 - loss: 2.2075
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.2077
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2724 - loss: 2.2080
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2721 - loss: 2.2083
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.2086
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 2.2089
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2712 - loss: 2.2092
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2710 - loss: 2.2095
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2097
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2705 - loss: 2.2099
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2702 - loss: 2.2102
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2700 - loss: 2.2104
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.2106
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.2108
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2693 - loss: 2.2110 - val_accuracy: 0.3184 - val_loss: 2.0990
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.0758
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2278  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2279
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2218
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2130
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2077
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.2027
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2639 - loss: 2.2004
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 2.1987
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.1971
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2642 - loss: 2.1952
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2645 - loss: 2.1938
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2649 - loss: 2.1922
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2652 - loss: 2.1913
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2655 - loss: 2.1905
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.1899
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2659 - loss: 2.1895
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2661 - loss: 2.1891
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2664 - loss: 2.1886
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2667 - loss: 2.1881
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.1877
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.1874
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2674 - loss: 2.1872
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.1870
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2677 - loss: 2.1869
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2678 - loss: 2.1868
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2679 - loss: 2.1866
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2681 - loss: 2.1864
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2682 - loss: 2.1862
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.1861
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2684 - loss: 2.1859
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.1856
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2686 - loss: 2.1854
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2688 - loss: 2.1852
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2689 - loss: 2.1849
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2691 - loss: 2.1846
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2692 - loss: 2.1843
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2693 - loss: 2.1841
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2695 - loss: 2.1838
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2696 - loss: 2.1835
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.1833
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2697 - loss: 2.1831
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2698 - loss: 2.1829
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2699 - loss: 2.1826
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2700 - loss: 2.1826 - val_accuracy: 0.3246 - val_loss: 2.0937
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.3125 - loss: 2.0617
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1829  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1744
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1769
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1827
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1837
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1839
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1839
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1837
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1836
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1828
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1816
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1803
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1790
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1777
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1759
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1745
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1731
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1720
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1709
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1699
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1690
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1683
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1676
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1670
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1663
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1658
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1653
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1648
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1645
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1642
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1639
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1637
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1634
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1632
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1630
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1628
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1625
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1624
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1622
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1620
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1618
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1616
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1614 - val_accuracy: 0.3292 - val_loss: 2.1209
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3312
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1685  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1441
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2908 - loss: 2.1325
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1275
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1247
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1230
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2957 - loss: 2.1223
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1220
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.1220
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 2.1223
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.1234
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1244
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1255
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1261
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1267
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1273
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2936 - loss: 2.1280
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1286
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1292
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1297
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1300
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1303
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1306
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1307
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1308
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1309
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1309
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1310
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1310
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1310
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2917 - loss: 2.1310
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2917 - loss: 2.1309
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2916 - loss: 2.1309
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2916 - loss: 2.1309
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2915 - loss: 2.1310
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2915 - loss: 2.1310
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1310
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1310
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1310
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1310
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1310
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1309
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1309 - val_accuracy: 0.3313 - val_loss: 2.0960
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0039
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3283 - loss: 2.1104  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3264 - loss: 2.1018
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3164 - loss: 2.1095
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3097 - loss: 2.1135
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3064 - loss: 2.1160
[1m 155/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3046 - loss: 2.1179
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3034 - loss: 2.1195
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 2.1207
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.1206
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 2.1205
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 2.1203
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.1199
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 2.1197
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3024 - loss: 2.1194
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3023 - loss: 2.1190
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3022 - loss: 2.1183
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 2.1176
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3019 - loss: 2.1172
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1171
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1172
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1174
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1175
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1176
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1178
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1180
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1181
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2993 - loss: 2.1182
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 2.1182
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1180
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1179
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2985 - loss: 2.1178
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1177
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1175
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1174
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1174
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1173
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1172
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 2.1171
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2977 - loss: 2.1170
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2976 - loss: 2.1169
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2975 - loss: 2.1168
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1167
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1166
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2973 - loss: 2.1166 - val_accuracy: 0.3119 - val_loss: 2.0959
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 1.8834
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0676  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0784
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3159 - loss: 2.0811
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0807
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0811
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0837
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0852
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0863
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0872
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0877
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0876
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0879
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0882
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0881
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0876
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0871
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0867
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0864
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3088 - loss: 2.0863
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3086 - loss: 2.0863
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 2.0863
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 2.0865
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3080 - loss: 2.0865
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3079 - loss: 2.0865
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3079 - loss: 2.0865
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3078 - loss: 2.0864
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0864
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0863
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0862
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3076 - loss: 2.0861
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0859
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0858
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3074 - loss: 2.0858
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3073 - loss: 2.0858
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3073 - loss: 2.0857
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3072 - loss: 2.0857
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0857
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0857
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0857
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0857
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0858
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3067 - loss: 2.0859
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0860
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0861 - val_accuracy: 0.3242 - val_loss: 2.1539
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.7242
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3285 - loss: 2.1606  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3059 - loss: 2.1417
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2976 - loss: 2.1302
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2958 - loss: 2.1213
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1152
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1124
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1106
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1078
[1m 233/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1055
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1034
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1022
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2929 - loss: 2.1011
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1001
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.0991
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2937 - loss: 2.0982
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 2.0971
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2945 - loss: 2.0957
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2949 - loss: 2.0944
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2953 - loss: 2.0934
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2956 - loss: 2.0923
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0913
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 2.0904
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2966 - loss: 2.0894
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 2.0885
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2971 - loss: 2.0876
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2974 - loss: 2.0867
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2976 - loss: 2.0860
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.0853
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 2.0848
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.0843
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.0839
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2985 - loss: 2.0836
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 2.0833
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2987 - loss: 2.0831
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2988 - loss: 2.0828
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2989 - loss: 2.0826
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2990 - loss: 2.0824
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 2.0822
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 2.0819
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2992 - loss: 2.0817
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2993 - loss: 2.0814
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2994 - loss: 2.0812
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2995 - loss: 2.0809
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2995 - loss: 2.0808 - val_accuracy: 0.3206 - val_loss: 2.1102

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 653ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 971us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:09[0m 849ms/step
[1m 47/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m 96/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m142/578[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m196/578[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m249/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m299/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m358/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 988us/step
[1m407/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 993us/step
[1m462/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 984us/step
[1m516/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 979us/step
[1m571/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 973us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 944us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 50/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m106/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 956us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 33.67 [%]
Global F1 score (validation) = 32.22 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.00945327 0.00526825 0.00664589 ... 0.02897466 0.02761409 0.00588576]
 [0.00124454 0.00139008 0.00161005 ... 0.16451141 0.0047301  0.0025911 ]
 [0.00080297 0.00085128 0.00150031 ... 0.00353819 0.00062872 0.0027811 ]
 ...
 [0.12932529 0.05403915 0.16781306 ... 0.00296445 0.16412485 0.15973666]
 [0.17757517 0.04927203 0.1831745  ... 0.00592785 0.09185553 0.12056998]
 [0.16439398 0.05188962 0.17099802 ... 0.00313007 0.17894328 0.08597458]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 40.38 [%]
Global accuracy score (test) = 29.23 [%]
Global F1 score (train) = 39.8 [%]
Global F1 score (test) = 27.8 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.26      0.35      0.30       184
 CAMINAR CON MÓVIL O LIBRO       0.13      0.11      0.12       184
       CAMINAR USUAL SPEED       0.19      0.11      0.14       184
            CAMINAR ZIGZAG       0.24      0.47      0.32       184
          DE PIE BARRIENDO       0.35      0.30      0.33       184
   DE PIE DOBLANDO TOALLAS       0.36      0.37      0.37       184
    DE PIE MOVIENDO LIBROS       0.35      0.17      0.23       184
          DE PIE USANDO PC       0.22      0.10      0.13       184
        FASE REPOSO CON K5       0.36      0.76      0.48       184
INCREMENTAL CICLOERGOMETRO       0.43      0.41      0.42       184
           SENTADO LEYENDO       0.20      0.18      0.19       184
         SENTADO USANDO PC       0.26      0.10      0.14       184
      SENTADO VIENDO LA TV       0.16      0.26      0.20       184
   SUBIR Y BAJAR ESCALERAS       0.41      0.20      0.27       184
                    TROTAR       0.53      0.51      0.52       161

                  accuracy                           0.29      2737
                 macro avg       0.30      0.29      0.28      2737
              weighted avg       0.30      0.29      0.28      2737


Accuracy capturado en la ejecución 22: 29.23 [%]
F1-score capturado en la ejecución 22: 27.8 [%]

=== EJECUCIÓN 23 ===

--- TRAIN (ejecución 23) ---

--- TEST (ejecución 23) ---
2025-11-07 13:24:41.342653: 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`.
2025-11-07 13:24:41.353887: 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 00:00:1762518281.367217 2821618 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762518281.371170 2821618 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762518281.381167 2821618 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518281.381186 2821618 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518281.381188 2821618 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518281.381189 2821618 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:24:41.384166: 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 00:00:1762518283.672077 2821618 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762518286.738277 2821727 service.cc:152] XLA service 0x77bd800025f0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762518286.738335 2821727 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:24:46.807352: 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 00:00:1762518287.247597 2821727 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762518289.762726 2821727 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43:41[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.2984
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0697 - loss: 3.3638        
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0701 - loss: 3.3567
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0704 - loss: 3.3454
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0709 - loss: 3.3343
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0729 - loss: 3.3180
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0744 - loss: 3.3024
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0758 - loss: 3.2902
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0770 - loss: 3.2786
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0782 - loss: 3.2688
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0794 - loss: 3.2594
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0802 - loss: 3.2526
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0812 - loss: 3.2451
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0820 - loss: 3.2379
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0829 - loss: 3.2310
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0837 - loss: 3.2241
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0846 - loss: 3.2173
[1m 472/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0853 - loss: 3.2107
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0861 - loss: 3.2037
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0869 - loss: 3.1973
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0876 - loss: 3.1917
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0884 - loss: 3.1857
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0892 - loss: 3.1797
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0901 - loss: 3.1736
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0908 - loss: 3.1682
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0916 - loss: 3.1631
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0924 - loss: 3.1579
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0932 - loss: 3.1522
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0940 - loss: 3.1473
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0948 - loss: 3.1420
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0955 - loss: 3.1372
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0962 - loss: 3.1323
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0969 - loss: 3.1280
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0977 - loss: 3.1233
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0984 - loss: 3.1188
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0991 - loss: 3.1144
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0999 - loss: 3.1096
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1007 - loss: 3.1051
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1014 - loss: 3.1006
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1022 - loss: 3.0957
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1029 - loss: 3.0915
[1m1128/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1036 - loss: 3.0871
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1043 - loss: 3.0831
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1043 - loss: 3.0829 - val_accuracy: 0.2498 - val_loss: 2.3193
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.2420
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2034 - loss: 2.6216  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2021 - loss: 2.6488
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1978 - loss: 2.6609
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1926 - loss: 2.6688
[1m 145/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1906 - loss: 2.6639
[1m 174/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1890 - loss: 2.6614
[1m 202/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1876 - loss: 2.6602
[1m 231/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1861 - loss: 2.6595
[1m 255/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1850 - loss: 2.6592
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1838 - loss: 2.6595
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6598
[1m 337/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1818 - loss: 2.6600
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1811 - loss: 2.6595
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1807 - loss: 2.6584
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1806 - loss: 2.6571
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1805 - loss: 2.6555
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6539
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6522
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1803 - loss: 2.6508
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1802 - loss: 2.6495
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1801 - loss: 2.6485
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1799 - loss: 2.6473
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.6463
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6452
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.6443
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.6432
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6422
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.6411
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1799 - loss: 2.6402
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1800 - loss: 2.6391
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.6380
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6369
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1806 - loss: 2.6359
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1808 - loss: 2.6347
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1809 - loss: 2.6337
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1812 - loss: 2.6324
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1814 - loss: 2.6313
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1816 - loss: 2.6302
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1817 - loss: 2.6291
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1819 - loss: 2.6279
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1821 - loss: 2.6268
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6258
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6255 - val_accuracy: 0.2770 - val_loss: 2.2533
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.2500 - loss: 2.5053
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1818 - loss: 2.5869  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1813 - loss: 2.5669
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1838 - loss: 2.5575
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1851 - loss: 2.5569
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1864 - loss: 2.5550
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1879 - loss: 2.5518
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1894 - loss: 2.5472
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1906 - loss: 2.5432
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1916 - loss: 2.5391
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1925 - loss: 2.5353
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1932 - loss: 2.5328
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1937 - loss: 2.5301
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1943 - loss: 2.5280
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1949 - loss: 2.5258
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1955 - loss: 2.5237
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1960 - loss: 2.5221
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1964 - loss: 2.5208
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1968 - loss: 2.5192
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1972 - loss: 2.5177
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1976 - loss: 2.5159
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1980 - loss: 2.5145
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1983 - loss: 2.5133
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1986 - loss: 2.5123
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1989 - loss: 2.5112
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1992 - loss: 2.5104
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1994 - loss: 2.5095
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1997 - loss: 2.5087
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2000 - loss: 2.5079
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2001 - loss: 2.5074
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2003 - loss: 2.5068
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2005 - loss: 2.5062
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2007 - loss: 2.5057
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2009 - loss: 2.5051
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.5044
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2013 - loss: 2.5038
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2015 - loss: 2.5031
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2016 - loss: 2.5025
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2018 - loss: 2.5018
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2020 - loss: 2.5012
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2021 - loss: 2.5005
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2023 - loss: 2.4999
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2025 - loss: 2.4993
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2025 - loss: 2.4992 - val_accuracy: 0.3000 - val_loss: 2.1834
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0885
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2244 - loss: 2.3034  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2121 - loss: 2.3504
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2123 - loss: 2.3638
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2136 - loss: 2.3730
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2134 - loss: 2.3830
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2125 - loss: 2.3924
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2120 - loss: 2.4003
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2112 - loss: 2.4067
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2108 - loss: 2.4107
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2108 - loss: 2.4132
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2107 - loss: 2.4160
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2103 - loss: 2.4184
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2100 - loss: 2.4204
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2097 - loss: 2.4219
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.4230
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2095 - loss: 2.4240
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2095 - loss: 2.4246
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2095 - loss: 2.4250
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.4251
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2096 - loss: 2.4252
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2098 - loss: 2.4253
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2099 - loss: 2.4252
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2100 - loss: 2.4250
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2102 - loss: 2.4247
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2103 - loss: 2.4245
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2105 - loss: 2.4243
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2106 - loss: 2.4241
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2107 - loss: 2.4237
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2109 - loss: 2.4233
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2110 - loss: 2.4229
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.4225
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2113 - loss: 2.4221
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2115 - loss: 2.4216
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2117 - loss: 2.4212
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2118 - loss: 2.4208
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2120 - loss: 2.4204
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2121 - loss: 2.4199
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2123 - loss: 2.4194
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2124 - loss: 2.4190
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2125 - loss: 2.4186
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2126 - loss: 2.4183
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2128 - loss: 2.4179
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2128 - loss: 2.4177 - val_accuracy: 0.3065 - val_loss: 2.1773
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1250 - loss: 2.6653
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2209 - loss: 2.3347  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2237 - loss: 2.3570
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3705
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2292 - loss: 2.3681
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3649
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3629
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3621
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3624
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2326 - loss: 2.3630
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3634
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3635
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3634
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3637
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3639
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3639
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2325 - loss: 2.3637
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2324 - loss: 2.3636
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3633
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3630
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2322 - loss: 2.3626
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2321 - loss: 2.3622
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3618
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3613
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3609
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3606
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3603
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3598
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3594
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3590
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3586
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3582
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3578
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3574
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3570
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3566
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3562
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3560
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3557
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3554
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3551
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3548
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3546 - val_accuracy: 0.3010 - val_loss: 2.1616
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.3741
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2138 - loss: 2.3080  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2260 - loss: 2.2955
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2305 - loss: 2.2944
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2331 - loss: 2.2962
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2361 - loss: 2.2948
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2383 - loss: 2.2934
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2396 - loss: 2.2927
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2408 - loss: 2.2918
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.2900
[1m 284/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.2885
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2876
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2870
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.2864
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2431 - loss: 2.2857
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2434 - loss: 2.2849
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2436 - loss: 2.2841
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2438 - loss: 2.2836
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2439 - loss: 2.2832
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2440 - loss: 2.2829
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2441 - loss: 2.2825
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2441 - loss: 2.2823
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2440 - loss: 2.2822
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2440 - loss: 2.2822
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2440 - loss: 2.2823
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2439 - loss: 2.2824
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2438 - loss: 2.2825
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2437 - loss: 2.2826
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.2827
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.2829
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.2831
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2833
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2836
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.2839
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.2842
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2429 - loss: 2.2845
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2848
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2851
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2426 - loss: 2.2853
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.2856
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2424 - loss: 2.2858
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2424 - loss: 2.2860 - val_accuracy: 0.3182 - val_loss: 2.1423
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3750 - loss: 2.1389
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3201 - loss: 2.2239  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2977 - loss: 2.2370
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2901 - loss: 2.2356
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 2.2376
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2781 - loss: 2.2436
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2748 - loss: 2.2471
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2717 - loss: 2.2503
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2694 - loss: 2.2526
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.2548
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.2560
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2647 - loss: 2.2571
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2580
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2585
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2625 - loss: 2.2587
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2621 - loss: 2.2590
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2617 - loss: 2.2592
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2594
[1m 482/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2612 - loss: 2.2597
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2610 - loss: 2.2599
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2600
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2601
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2602
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2603
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2604
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2605
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2605
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2607
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2608
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2608
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2609
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2610
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2611
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2611
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2612
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2612
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2611
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2610
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2610
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2610
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2610
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2610
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2609
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2609 - val_accuracy: 0.2998 - val_loss: 2.1475
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1875 - loss: 2.1736
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2580 - loss: 2.2602  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2666
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2559
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2521
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2504
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2481
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2533 - loss: 2.2467
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2461
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2451
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2437
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2428
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2419
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2550 - loss: 2.2413
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2408
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2403
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2398
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2389
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2382
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2373
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2567 - loss: 2.2366
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2569 - loss: 2.2359
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2570 - loss: 2.2354
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2572 - loss: 2.2350
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2574 - loss: 2.2345
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2576 - loss: 2.2340
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2334
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2327
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2321
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2587 - loss: 2.2315
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2590 - loss: 2.2309
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2592 - loss: 2.2303
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2299
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2294
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2291
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2287
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2284
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2281
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2277
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2274
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2271
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2268
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2266
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2265 - val_accuracy: 0.3260 - val_loss: 2.1060
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1606
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2493 - loss: 2.1798  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2637 - loss: 2.1640
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.1542
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1518
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2733 - loss: 2.1532
[1m 172/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2735 - loss: 2.1544
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1549
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2744 - loss: 2.1559
[1m 255/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2746 - loss: 2.1569
[1m 283/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2748 - loss: 2.1580
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2752 - loss: 2.1590
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2754 - loss: 2.1600
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 2.1606
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1611
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2761 - loss: 2.1619
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2763 - loss: 2.1626
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1633
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1639
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1644
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1651
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1659
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1665
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1670
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1674
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1679
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1683
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1686
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1689
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2775 - loss: 2.1693
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1696
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2777 - loss: 2.1698
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1701
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1704
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1707
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1710
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1713
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1716
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1719
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1722
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1725
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1728
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1728 - val_accuracy: 0.3439 - val_loss: 2.1054
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0488
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1990  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2790 - loss: 2.2157
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2774 - loss: 2.2166
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.2110
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2762 - loss: 2.2090
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2752 - loss: 2.2071
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.2068
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.2067
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2730 - loss: 2.2066
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 2.2064
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 2.2058
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2728 - loss: 2.2049
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2729 - loss: 2.2040
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2729 - loss: 2.2033
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2730 - loss: 2.2025
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2731 - loss: 2.2017
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2732 - loss: 2.2007
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.1999
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2735 - loss: 2.1989
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2737 - loss: 2.1979
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2739 - loss: 2.1968
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1959
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2744 - loss: 2.1948
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2746 - loss: 2.1939
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2748 - loss: 2.1930
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2750 - loss: 2.1921
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2752 - loss: 2.1914
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2754 - loss: 2.1907
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2755 - loss: 2.1901
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2757 - loss: 2.1894
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2759 - loss: 2.1888
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2761 - loss: 2.1883
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2762 - loss: 2.1879
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2763 - loss: 2.1875
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1871
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1866
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1862
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1858
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1855
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1850
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1846
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1842
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1840 - val_accuracy: 0.3445 - val_loss: 2.1057
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.1429
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2591 - loss: 2.1577  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2608 - loss: 2.1623
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2638 - loss: 2.1575
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2678 - loss: 2.1516
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2717 - loss: 2.1451
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2738 - loss: 2.1407
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2752 - loss: 2.1387
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2761 - loss: 2.1372
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1360
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2777 - loss: 2.1349
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1347
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1348
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1349
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1348
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1347
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1347
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1346
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1346
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1347
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1345
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1341
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1339
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1339
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1338
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1337
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1336
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1335
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1334
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1334
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1334
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1335
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1336
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1337
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1337
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1338
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1339
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1339
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1339
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1339
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1340
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1340
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1341
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1341 - val_accuracy: 0.3359 - val_loss: 2.1031
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.4375 - loss: 1.8027
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0521  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0824
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2954 - loss: 2.1007
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1104
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2908 - loss: 2.1166
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1207
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1226
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1227
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1229
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1234
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1238
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1229
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2901 - loss: 2.1219
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2907 - loss: 2.1212
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2911 - loss: 2.1209
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2915 - loss: 2.1206
[1m 470/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1204
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1203
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1203
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1204
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1205
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1207
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1209
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2928 - loss: 2.1210
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 2.1210
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1209
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1208
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1206
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1204
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1201
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 2.1200
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1199
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2938 - loss: 2.1197
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1196
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1195
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2940 - loss: 2.1194
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1193
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1193
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1192
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1192
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1191
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1190
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1190 - val_accuracy: 0.3488 - val_loss: 2.1078
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 1.8978
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3107 - loss: 1.9978  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0501
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0617
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0613
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 2.0607
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0625
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0658
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0677
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0692
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0701
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0709
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0715
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0721
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0726
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0729
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0734
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 2.0741
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3081 - loss: 2.0748
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3078 - loss: 2.0757
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0765
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 2.0773
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0779
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0785
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3067 - loss: 2.0792
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0801
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0811
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0818
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0825
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3056 - loss: 2.0833
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0839
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3053 - loss: 2.0844
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0849
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3050 - loss: 2.0853
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3049 - loss: 2.0857
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0860
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0862
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0865
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0867
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0869
[1m1102/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0871
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0872
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0874
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3046 - loss: 2.0874 - val_accuracy: 0.3383 - val_loss: 2.0821
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.6250 - loss: 1.7758
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3026 - loss: 2.1268  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3044 - loss: 2.0985
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0943
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3074 - loss: 2.0911
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.0887
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3075 - loss: 2.0868
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0860
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3067 - loss: 2.0850
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0846
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0842
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0837
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3057 - loss: 2.0832
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0831
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0830
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0829
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0828
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0827
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 2.0828
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0830
[1m 553/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3033 - loss: 2.0831
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0831
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0832
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0831
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0830
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0828
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0826
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0825
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0823
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0821
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0820
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0818
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0817
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0816
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0815
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0814
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0813
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0812
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0811
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0811
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0810
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0809
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0808 - val_accuracy: 0.3478 - val_loss: 2.1150
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.6383
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3615 - loss: 2.0766  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3442 - loss: 2.0800
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3394 - loss: 2.0710
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3361 - loss: 2.0657
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 2.0646
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 2.0667
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 2.0688
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0697
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0691
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0680
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0673
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0669
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0665
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0658
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0652
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3218 - loss: 2.0648
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0646
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0644
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0642
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0642
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0642
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0641
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0639
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0637
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0637
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 2.0635
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3188 - loss: 2.0634
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3187 - loss: 2.0633
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3185 - loss: 2.0633
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0633
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3183 - loss: 2.0632
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0631
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0630
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0630
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0629
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0628
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0628
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0628
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0627
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0626
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0626
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0626 - val_accuracy: 0.3337 - val_loss: 2.1373
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.4563
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3116 - loss: 2.1980  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3072 - loss: 2.1564
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3071 - loss: 2.1389
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3096 - loss: 2.1224
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.1129
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.1037
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0976
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0926
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0885
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0846
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0818
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0790
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0767
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0745
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0723
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0703
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0686
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0669
[1m 525/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0656
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0643
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0632
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0622
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0611
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0601
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0591
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0582
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0574
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0566
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0560
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0555
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0550
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0545
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0540
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0536
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0533
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3148 - loss: 2.0530
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0526
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0523
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0520
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0518
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0515
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0514 - val_accuracy: 0.3387 - val_loss: 2.1099
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3750 - loss: 1.9247
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0360  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0391
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3392 - loss: 2.0313
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3444 - loss: 2.0209
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 2.0169
[1m 173/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3474 - loss: 2.0135
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3478 - loss: 2.0117
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3478 - loss: 2.0104
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3475 - loss: 2.0096
[1m 283/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3470 - loss: 2.0092
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3466 - loss: 2.0092
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3462 - loss: 2.0092
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3457 - loss: 2.0089
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3453 - loss: 2.0087
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3450 - loss: 2.0084
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3447 - loss: 2.0080
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3444 - loss: 2.0079
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3440 - loss: 2.0077
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3438 - loss: 2.0075
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3435 - loss: 2.0073
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3432 - loss: 2.0073
[1m 609/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3428 - loss: 2.0073
[1m 636/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3425 - loss: 2.0074
[1m 663/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3421 - loss: 2.0075
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3417 - loss: 2.0078
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3414 - loss: 2.0081
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3410 - loss: 2.0084
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3407 - loss: 2.0087
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3405 - loss: 2.0089
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3402 - loss: 2.0091
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 2.0094
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3397 - loss: 2.0096
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3394 - loss: 2.0098
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3392 - loss: 2.0099
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3390 - loss: 2.0101
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3388 - loss: 2.0103
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3386 - loss: 2.0105
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3384 - loss: 2.0107
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 2.0109
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3380 - loss: 2.0112
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 2.0114
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3377 - loss: 2.0116 - val_accuracy: 0.3441 - val_loss: 2.1370
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4912
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2773 - loss: 2.0779  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2903 - loss: 2.0567
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2988 - loss: 2.0429
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0366
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0337
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0313
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0296
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3160 - loss: 2.0290
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0284
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3186 - loss: 2.0270
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0258
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0252
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0250
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0249
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0247
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0247
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0246
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0244
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0245
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0245
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3237 - loss: 2.0246
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3238 - loss: 2.0247
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3238 - loss: 2.0247
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0246
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0245
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0244
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0242
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0240
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3247 - loss: 2.0237
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0234
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0231
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0227
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0223
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0219
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0215
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0213
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0211
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0208
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0206
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0204
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0203
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0201
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0200 - val_accuracy: 0.3458 - val_loss: 2.1216

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m55s[0m 651ms/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:07[0m 846ms/step
[1m 50/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m105/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 972us/step
[1m158/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 966us/step
[1m211/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 961us/step
[1m265/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 956us/step
[1m325/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 935us/step
[1m380/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 932us/step
[1m435/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 931us/step
[1m488/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 933us/step
[1m548/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 923us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 16ms/step
[1m43/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 51/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m109/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 939us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 32.02 [%]
Global F1 score (validation) = 31.12 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.05015995 0.01846535 0.02551745 ... 0.04289724 0.03708976 0.02474424]
 [0.0072641  0.00305265 0.00322759 ... 0.0954156  0.01428622 0.01250925]
 [0.0033004  0.00130006 0.00069186 ... 0.00511654 0.00059474 0.00182929]
 ...
 [0.182264   0.04786318 0.16053428 ... 0.00616165 0.18415771 0.11188802]
 [0.17500183 0.06473451 0.09850589 ... 0.02928631 0.11713699 0.07587711]
 [0.13062894 0.06961638 0.17046766 ... 0.00933508 0.15803695 0.06636243]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 36.24 [%]
Global accuracy score (test) = 28.5 [%]
Global F1 score (train) = 36.39 [%]
Global F1 score (test) = 28.18 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.29      0.39      0.33       184
 CAMINAR CON MÓVIL O LIBRO       0.31      0.30      0.30       184
       CAMINAR USUAL SPEED       0.15      0.08      0.10       184
            CAMINAR ZIGZAG       0.23      0.27      0.25       184
          DE PIE BARRIENDO       0.30      0.24      0.27       184
   DE PIE DOBLANDO TOALLAS       0.36      0.43      0.39       184
    DE PIE MOVIENDO LIBROS       0.20      0.20      0.20       184
          DE PIE USANDO PC       0.15      0.19      0.17       184
        FASE REPOSO CON K5       0.46      0.56      0.51       184
INCREMENTAL CICLOERGOMETRO       0.60      0.35      0.44       184
           SENTADO LEYENDO       0.17      0.08      0.11       184
         SENTADO USANDO PC       0.20      0.27      0.23       184
      SENTADO VIENDO LA TV       0.19      0.21      0.20       184
   SUBIR Y BAJAR ESCALERAS       0.24      0.24      0.24       184
                    TROTAR       0.48      0.50      0.49       161

                  accuracy                           0.28      2737
                 macro avg       0.29      0.29      0.28      2737
              weighted avg       0.29      0.28      0.28      2737


Accuracy capturado en la ejecución 23: 28.5 [%]
F1-score capturado en la ejecución 23: 28.18 [%]

=== EJECUCIÓN 24 ===

--- TRAIN (ejecución 24) ---

--- TEST (ejecución 24) ---
2025-11-07 13:25:52.360522: 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`.
2025-11-07 13:25:52.371728: 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 00:00:1762518352.384975 2824683 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762518352.389121 2824683 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762518352.399300 2824683 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518352.399319 2824683 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518352.399321 2824683 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518352.399323 2824683 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:25:52.402627: 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 00:00:1762518354.701080 2824683 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762518357.796776 2824786 service.cc:152] XLA service 0x7c3b0c01b1b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762518357.796816 2824786 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:25:57.861837: 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 00:00:1762518358.285545 2824786 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762518360.833024 2824786 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:49[0m 5s/step - accuracy: 0.1250 - loss: 3.0830
[1m  20/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m3s[0m 3ms/step - accuracy: 0.0682 - loss: 3.5182    
[1m  42/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0684 - loss: 3.5145
[1m  70/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0674 - loss: 3.5086
[1m  98/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0662 - loss: 3.4894
[1m 124/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0664 - loss: 3.4674
[1m 151/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0669 - loss: 3.4450
[1m 177/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0681 - loss: 3.4239
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0697 - loss: 3.4013
[1m 234/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0709 - loss: 3.3844
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0721 - loss: 3.3674
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0733 - loss: 3.3521
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0745 - loss: 3.3378
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0755 - loss: 3.3273
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0768 - loss: 3.3155
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0782 - loss: 3.3043
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0795 - loss: 3.2942
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0811 - loss: 3.2837
[1m 476/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0825 - loss: 3.2742
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0840 - loss: 3.2642
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0855 - loss: 3.2548
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0870 - loss: 3.2450
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0883 - loss: 3.2360
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0895 - loss: 3.2282
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0907 - loss: 3.2204
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0918 - loss: 3.2129
[1m 691/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0929 - loss: 3.2056
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0941 - loss: 3.1977
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0952 - loss: 3.1905
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0963 - loss: 3.1834
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0972 - loss: 3.1769
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0982 - loss: 3.1704
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0991 - loss: 3.1645
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1001 - loss: 3.1584
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1008 - loss: 3.1533
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1017 - loss: 3.1474
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1026 - loss: 3.1418
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1034 - loss: 3.1360
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1042 - loss: 3.1314
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1050 - loss: 3.1259
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1057 - loss: 3.1209
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1064 - loss: 3.1168
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1071 - loss: 3.1122
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1078 - loss: 3.1076
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1080 - loss: 3.1066
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1080 - loss: 3.1064 - val_accuracy: 0.2404 - val_loss: 2.3891
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.2500 - loss: 2.9702
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1681 - loss: 2.7614  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1703 - loss: 2.7394
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1722 - loss: 2.7361
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1724 - loss: 2.7335
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1723 - loss: 2.7293
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1728 - loss: 2.7212
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1735 - loss: 2.7133
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1743 - loss: 2.7060
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1751 - loss: 2.6988
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1756 - loss: 2.6934
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1762 - loss: 2.6885
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1767 - loss: 2.6846
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1770 - loss: 2.6814
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1773 - loss: 2.6786
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1776 - loss: 2.6754
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.6725
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6699
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6675
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1783 - loss: 2.6652
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.6633
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1785 - loss: 2.6613
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1787 - loss: 2.6594
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1788 - loss: 2.6578
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1789 - loss: 2.6561
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1791 - loss: 2.6543
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.6528
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1793 - loss: 2.6512
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.6499
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6485
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.6471
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6458
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.6446
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1799 - loss: 2.6433
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1801 - loss: 2.6420
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1802 - loss: 2.6409
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1803 - loss: 2.6397
[1m1003/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1804 - loss: 2.6386
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1805 - loss: 2.6375
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1806 - loss: 2.6366
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1807 - loss: 2.6354
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1808 - loss: 2.6345
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1808 - loss: 2.6335
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1809 - loss: 2.6326 - val_accuracy: 0.2642 - val_loss: 2.2951
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.4448
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2029 - loss: 2.4872  
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2041 - loss: 2.4766
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2027 - loss: 2.4775
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2016 - loss: 2.4850
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2013 - loss: 2.4879
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2024 - loss: 2.4890
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2033 - loss: 2.4903
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2036 - loss: 2.4916
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2040 - loss: 2.4927
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2040 - loss: 2.4941
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2040 - loss: 2.4953
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2039 - loss: 2.4965
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2037 - loss: 2.4974
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2035 - loss: 2.4982
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2034 - loss: 2.4985
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2033 - loss: 2.4987
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2032 - loss: 2.4990
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2031 - loss: 2.4992
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2030 - loss: 2.4994
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2028 - loss: 2.4995
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2027 - loss: 2.4995
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2027 - loss: 2.4993
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.4990
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2025 - loss: 2.4987
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2025 - loss: 2.4983
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2025 - loss: 2.4978
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2025 - loss: 2.4973
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2025 - loss: 2.4967
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2025 - loss: 2.4962
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2026 - loss: 2.4957
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2027 - loss: 2.4951
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2028 - loss: 2.4945
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2029 - loss: 2.4938
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2030 - loss: 2.4931
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2031 - loss: 2.4925
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2032 - loss: 2.4918
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2034 - loss: 2.4912
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2035 - loss: 2.4905
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2037 - loss: 2.4898
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2038 - loss: 2.4891
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2039 - loss: 2.4885
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2041 - loss: 2.4877
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2041 - loss: 2.4877 - val_accuracy: 0.2766 - val_loss: 2.2304
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.5542
[1m  22/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1932 - loss: 2.4487  
[1m  47/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2015 - loss: 2.4282
[1m  74/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2071 - loss: 2.4287
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2097 - loss: 2.4273
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2119 - loss: 2.4207
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2139 - loss: 2.4143
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2152 - loss: 2.4103
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2160 - loss: 2.4070
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2168 - loss: 2.4049
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2173 - loss: 2.4038
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4031
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4026
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4019
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4014
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2197 - loss: 2.4010
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.4004
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2204 - loss: 2.3999
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2208 - loss: 2.3995
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2211 - loss: 2.3990
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2213 - loss: 2.3986
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2215 - loss: 2.3982
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2216 - loss: 2.3979
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2218 - loss: 2.3976
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2219 - loss: 2.3974
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2220 - loss: 2.3971
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2221 - loss: 2.3969
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2221 - loss: 2.3967
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3966
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3965
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3964
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3963
[1m 856/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2222 - loss: 2.3962
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3960
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3958
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3956
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3954
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3953
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3951
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3950
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3949
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3948
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3947
[1m1150/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3946
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3946 - val_accuracy: 0.2807 - val_loss: 2.1941
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.3252
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2759 - loss: 2.2762  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2638 - loss: 2.3085
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2556 - loss: 2.3250
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2510 - loss: 2.3295
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2491 - loss: 2.3297
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2493 - loss: 2.3287
[1m 180/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.3282
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2481 - loss: 2.3285
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2473 - loss: 2.3287
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2469 - loss: 2.3286
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2466 - loss: 2.3287
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2464 - loss: 2.3290
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.3298
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2456 - loss: 2.3304
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2453 - loss: 2.3310
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2451 - loss: 2.3312
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2449 - loss: 2.3313
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2447 - loss: 2.3316
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2445 - loss: 2.3316
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2444 - loss: 2.3316
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2442 - loss: 2.3316
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2440 - loss: 2.3318
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2438 - loss: 2.3319
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2437 - loss: 2.3321
[1m 666/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.3322
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.3323
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3323
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3323
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3324
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2432 - loss: 2.3324
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3325
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3326
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.3326
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.3326
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2429 - loss: 2.3327
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2428 - loss: 2.3327
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3327
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3327
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2426 - loss: 2.3327
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2426 - loss: 2.3326
[1m1103/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3326
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3325
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3324 - val_accuracy: 0.2773 - val_loss: 2.1913
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3750 - loss: 2.2880
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2316 - loss: 2.3511  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2434 - loss: 2.3276
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2466 - loss: 2.3216
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2484 - loss: 2.3178
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.3137
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.3115
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2517 - loss: 2.3099
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2518 - loss: 2.3090
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2516 - loss: 2.3083
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2513 - loss: 2.3073
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2511 - loss: 2.3064
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.3056
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2510 - loss: 2.3051
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.3047
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2505 - loss: 2.3044
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.3042
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2500 - loss: 2.3038
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.3035
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.3030
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.3028
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2494 - loss: 2.3026
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2493 - loss: 2.3024
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2491 - loss: 2.3023
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2490 - loss: 2.3021
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2488 - loss: 2.3020
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.3019
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.3018
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.3015
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2484 - loss: 2.3013
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2483 - loss: 2.3011
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2482 - loss: 2.3009
[1m 879/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2482 - loss: 2.3007
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2481 - loss: 2.3005
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2480 - loss: 2.3003
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2480 - loss: 2.3001
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2999
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2996
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2992
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2989
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2985
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2982
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2979
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2979 - val_accuracy: 0.2958 - val_loss: 2.1735
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1307
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2299  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2473 - loss: 2.2424
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2465 - loss: 2.2484
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.2528
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2563
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2453 - loss: 2.2593
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2458 - loss: 2.2605
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.2612
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2465 - loss: 2.2612
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2613
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2476 - loss: 2.2614
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2611
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2484 - loss: 2.2607
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2604
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2601
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.2599
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2494 - loss: 2.2596
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2593
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2591
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.2589
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2505 - loss: 2.2586
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2583
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2582
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2581
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2580
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2514 - loss: 2.2579
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2516 - loss: 2.2578
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2518 - loss: 2.2577
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2520 - loss: 2.2576
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2522 - loss: 2.2575
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2524 - loss: 2.2575
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2526 - loss: 2.2574
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2528 - loss: 2.2572
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2530 - loss: 2.2570
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2569
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2566
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2536 - loss: 2.2564
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2563
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2561
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2559
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2558
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2543 - loss: 2.2556
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2555 - val_accuracy: 0.3041 - val_loss: 2.1479
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1875 - loss: 2.1302
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2680 - loss: 2.2080  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2613 - loss: 2.2285
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2396
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2584 - loss: 2.2394
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2364
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2595 - loss: 2.2344
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2333
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2326
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2599 - loss: 2.2322
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2319
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2321
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2322
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2319
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2612 - loss: 2.2318
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2319
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2318
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2319
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2319
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2319
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2319
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2318
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2317
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2316
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2315
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2313
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2311
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2309
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2306
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2303
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2301
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2298
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2295
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2292
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2287
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2284
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2281
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2278
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2617 - loss: 2.2275
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2272
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2269
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2620 - loss: 2.2266
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2620 - loss: 2.2263
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2621 - loss: 2.2261 - val_accuracy: 0.3016 - val_loss: 2.1251
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.0221
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2768 - loss: 2.2360  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2810 - loss: 2.2042
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1948
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1886
[1m 125/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1848
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1817
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1790
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1778
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1774
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1768
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1766
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1769
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1773
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1776
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1780
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1784
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1788
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1793
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1799
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1805
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1809
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1813
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1817
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1821
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1824
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1827
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1830
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1832
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1834
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1835
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2815 - loss: 2.1836
[1m 866/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1837
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1837
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1839
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1840
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1841
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1842
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1843
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1843
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1844
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1844
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1845
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1845
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1845 - val_accuracy: 0.3238 - val_loss: 2.1001
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.5000 - loss: 1.9049
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3109 - loss: 2.1203  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2902 - loss: 2.1479
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1608
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1675
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2777 - loss: 2.1743
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1767
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1779
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1785
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1792
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1798
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1803
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1802
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1804
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1809
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1811
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1812
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1810
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.1808
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1806
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1803
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1800
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1796
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1793
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1788
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2781 - loss: 2.1783
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1778
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1774
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1770
[1m 784/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1767
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1764
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1761
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2791 - loss: 2.1759
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2792 - loss: 2.1756
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2792 - loss: 2.1754
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1752
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1749
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1746
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1743
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1740
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1737
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1735
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1733
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1731 - val_accuracy: 0.3099 - val_loss: 2.1233
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.7584
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2802 - loss: 2.0170  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2756 - loss: 2.0523
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2756 - loss: 2.0628
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2753 - loss: 2.0747
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2750 - loss: 2.0869
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2750 - loss: 2.0948
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2751 - loss: 2.1022
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2752 - loss: 2.1080
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2756 - loss: 2.1128
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2759 - loss: 2.1162
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.1189
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1210
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1225
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1243
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1262
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1273
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1287
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1298
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1303
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1309
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1313
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1317
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1321
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1325
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1329
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1334
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1338
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1340
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1343
[1m 824/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1346
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1348
[1m 880/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1350
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1351
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1352
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1352
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1353
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1355
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1356
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1357
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1358
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1359
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1360
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1360 - val_accuracy: 0.3149 - val_loss: 2.1117
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.3125 - loss: 1.9199
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2706 - loss: 2.0698  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2728 - loss: 2.0931
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2786 - loss: 2.0977
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1048
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1120
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1159
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1188
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1205
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1220
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1234
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1244
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1255
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1262
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1265
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1266
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1265
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1262
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1262
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1262
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1263
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1265
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1265
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1265
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1264
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1262
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1259
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1257
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1255
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1255
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1254
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2880 - loss: 2.1252
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1250
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1248
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2887 - loss: 2.1246
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1244
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1242
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1240
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1238
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1235
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1233
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2899 - loss: 2.1231
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2900 - loss: 2.1229
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2901 - loss: 2.1228 - val_accuracy: 0.3147 - val_loss: 2.1119
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0161
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3356 - loss: 2.0172  
[1m  60/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3335 - loss: 2.0220
[1m  89/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3366 - loss: 2.0189
[1m 119/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3342 - loss: 2.0266
[1m 145/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 2.0316
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 2.0381
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0441
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0489
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0535
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0578
[1m 310/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0614
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0640
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0667
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 2.0688
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3160 - loss: 2.0706
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3156 - loss: 2.0718
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0726
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0733
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 2.0740
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3146 - loss: 2.0746
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0752
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0756
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0762
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0767
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0773
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0779
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3133 - loss: 2.0785
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0790
[1m 801/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0796
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0803
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0809
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0815
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0820
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0824
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0828
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0832
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0835
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0839
[1m1076/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0842
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0845
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0847
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0849 - val_accuracy: 0.3081 - val_loss: 2.1315
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m29s[0m 26ms/step - accuracy: 0.3750 - loss: 1.8800
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2911 - loss: 2.0768  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2923 - loss: 2.0879
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 2.0836
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0831
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0831
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0823
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0824
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0836
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0849
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0857
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 2.0860
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.0863
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.0866
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 2.0871
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3039 - loss: 2.0876
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0878
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0878
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0878
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3037 - loss: 2.0877
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0877
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0875
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0872
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0870
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0868
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0867
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0866
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0865
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0865
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0864
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0864
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0865
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0865
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0865
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0865
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0865
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0865
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0863
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0863
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0862
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0862
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0860
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0859
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0858 - val_accuracy: 0.3202 - val_loss: 2.0804
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.5000 - loss: 1.7401
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3555 - loss: 2.0420  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3384 - loss: 2.0650
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3309 - loss: 2.0717
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0717
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0689
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0660
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0641
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0626
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0612
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0604
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0604
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0608
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0610
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0610
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 2.0611
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3188 - loss: 2.0615
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3186 - loss: 2.0617
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0619
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0622
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3181 - loss: 2.0625
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0627
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3177 - loss: 2.0629
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0630
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0630
[1m 677/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0629
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0630
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0631
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0632
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0632
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0633
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0633
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0633
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0633
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0634
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0634
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0634
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0633
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0633
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0632
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0632
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0632
[1m1136/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0632
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0631 - val_accuracy: 0.3167 - val_loss: 2.1074
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.6239
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3314 - loss: 2.0271  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0539
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0591
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3183 - loss: 2.0573
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0516
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0508
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 2.0495
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3187 - loss: 2.0489
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0484
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3180 - loss: 2.0486
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0490
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0492
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0491
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0487
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0481
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3174 - loss: 2.0476
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0470
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3178 - loss: 2.0465
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3180 - loss: 2.0463
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0463
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0460
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 2.0458
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3187 - loss: 2.0456
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3189 - loss: 2.0454
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3190 - loss: 2.0453
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0453
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3191 - loss: 2.0453
[1m 759/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0453
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0454
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0454
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0455
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0455
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0455
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0454
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0452
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0452
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0451
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0450
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0449
[1m1080/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0448
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0447
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0446
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0445 - val_accuracy: 0.3178 - val_loss: 2.0790
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.0572
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0442  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0278
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3183 - loss: 2.0359
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0400
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3190 - loss: 2.0390
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0390
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0387
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0376
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0369
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0371
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0374
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0374
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0373
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0373
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0374
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0372
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0369
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0368
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0367
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0368
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0368
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0369
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0370
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0369
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0368
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0367
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0366
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0366
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0366
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0366
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0366
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0366
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0366
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0366
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0366
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0366
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0365
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0364
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0364
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0363
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0363
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0363
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0364
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0364 - val_accuracy: 0.3310 - val_loss: 2.0695
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.0504
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0179  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3225 - loss: 2.0274
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0282
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0267
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3284 - loss: 2.0268
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 2.0259
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3300 - loss: 2.0260
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0260
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0255
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3314 - loss: 2.0250
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0244
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0238
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0233
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3315 - loss: 2.0229
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 2.0227
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0224
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3309 - loss: 2.0220
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0216
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0212
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0207
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0201
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0195
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0190
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0185
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3305 - loss: 2.0181
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 2.0177
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 2.0175
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0173
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0170
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0168
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0166
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0164
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0162
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0161
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3302 - loss: 2.0159
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 2.0158
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 2.0156
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 2.0156
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 2.0155
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 2.0154
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 2.0154
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3298 - loss: 2.0154
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3298 - loss: 2.0154
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3297 - loss: 2.0154 - val_accuracy: 0.3298 - val_loss: 2.0597
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.5190
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2682 - loss: 2.1090  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2829 - loss: 2.0817
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2895 - loss: 2.0675
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2938 - loss: 2.0583
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 2.0511
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.0470
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0411
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3060 - loss: 2.0365
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3082 - loss: 2.0331
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0305
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0276
[1m 333/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3131 - loss: 2.0251
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0231
[1m 388/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0212
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 2.0191
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0173
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3184 - loss: 2.0157
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0144
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0131
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0120
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3212 - loss: 2.0110
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0100
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0091
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0080
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3234 - loss: 2.0071
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3240 - loss: 2.0061
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3244 - loss: 2.0054
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3248 - loss: 2.0048
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0042
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0037
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0033
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0029
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0025
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0023
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0021
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0021
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0020
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0020
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0019
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0019
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0019
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0019
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3278 - loss: 2.0019 - val_accuracy: 0.3266 - val_loss: 2.1032
Epoch 20/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.6654
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3147 - loss: 2.1449  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3156 - loss: 2.0908
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0669
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0566
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0444
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0354
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3179 - loss: 2.0298
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3188 - loss: 2.0256
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0229
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0205
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3200 - loss: 2.0186
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3203 - loss: 2.0169
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0150
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0136
[1m 401/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0121
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0105
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0092
[1m 482/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0082
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3235 - loss: 2.0072
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0065
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0058
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3245 - loss: 2.0054
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3247 - loss: 2.0050
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0047
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3250 - loss: 2.0045
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0044
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0042
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3255 - loss: 2.0039
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3256 - loss: 2.0037
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0036
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0035
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0034
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3259 - loss: 2.0034
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3260 - loss: 2.0032
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3261 - loss: 2.0031
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3262 - loss: 2.0029
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0027
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0025
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3264 - loss: 2.0023
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3265 - loss: 2.0022
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0021
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3266 - loss: 2.0020
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0018 - val_accuracy: 0.3151 - val_loss: 2.1021
Epoch 21/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 24ms/step - accuracy: 0.5625 - loss: 1.8090
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3464 - loss: 1.9971  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3426 - loss: 2.0023
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3438 - loss: 2.0050
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3452 - loss: 2.0033
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3464 - loss: 2.0005
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9981
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3476 - loss: 1.9964
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3473 - loss: 1.9960
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3468 - loss: 1.9959
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3466 - loss: 1.9952
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3466 - loss: 1.9945
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3467 - loss: 1.9933
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3467 - loss: 1.9922
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3467 - loss: 1.9912
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3467 - loss: 1.9904
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.9897
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 1.9889
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3461 - loss: 1.9882
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3460 - loss: 1.9874
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3459 - loss: 1.9866
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3458 - loss: 1.9858
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3458 - loss: 1.9849
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3458 - loss: 1.9841
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3458 - loss: 1.9836
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3458 - loss: 1.9831
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3458 - loss: 1.9827
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3458 - loss: 1.9824
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3457 - loss: 1.9822
[1m 773/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3456 - loss: 1.9820
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3455 - loss: 1.9818
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3454 - loss: 1.9815
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3453 - loss: 1.9812
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3452 - loss: 1.9809
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3452 - loss: 1.9806
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3451 - loss: 1.9803
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3450 - loss: 1.9799
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3449 - loss: 1.9797
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3449 - loss: 1.9793
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3448 - loss: 1.9791
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3448 - loss: 1.9788
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3447 - loss: 1.9786
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3446 - loss: 1.9783
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3446 - loss: 1.9781 - val_accuracy: 0.3355 - val_loss: 2.0959
Epoch 22/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.2500 - loss: 2.0154
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3303 - loss: 1.9846  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3318 - loss: 1.9991
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3340 - loss: 1.9972
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3359 - loss: 1.9947
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3376 - loss: 1.9924
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3392 - loss: 1.9893
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3405 - loss: 1.9871
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3418 - loss: 1.9853
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3429 - loss: 1.9838
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3439 - loss: 1.9823
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3445 - loss: 1.9815
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3451 - loss: 1.9808
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3455 - loss: 1.9800
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3456 - loss: 1.9794
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3459 - loss: 1.9784
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3460 - loss: 1.9775
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3460 - loss: 1.9767
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3461 - loss: 1.9756
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9748
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3462 - loss: 1.9740
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3463 - loss: 1.9732
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3464 - loss: 1.9723
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3465 - loss: 1.9715
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3466 - loss: 1.9707
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3467 - loss: 1.9701
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3468 - loss: 1.9693
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3469 - loss: 1.9686
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3470 - loss: 1.9680
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.9674
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3471 - loss: 1.9668
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9664
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9660
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3473 - loss: 1.9657
[1m 918/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3473 - loss: 1.9655
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9653
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9652
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9651
[1m1025/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9650
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9649
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9648
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9648
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9647
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3472 - loss: 1.9647 - val_accuracy: 0.3171 - val_loss: 2.1171
Epoch 23/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.8900
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3274 - loss: 1.9757  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3347 - loss: 1.9561
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3427 - loss: 1.9447
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3476 - loss: 1.9407
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3513 - loss: 1.9394
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3530 - loss: 1.9400
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3546 - loss: 1.9397
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3554 - loss: 1.9402
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3561 - loss: 1.9411
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3568 - loss: 1.9413
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3576 - loss: 1.9413
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3586 - loss: 1.9407
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3592 - loss: 1.9401
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3597 - loss: 1.9397
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3600 - loss: 1.9393
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3601 - loss: 1.9391
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3602 - loss: 1.9390
[1m 482/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3601 - loss: 1.9390
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3599 - loss: 1.9394
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3596 - loss: 1.9399
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3593 - loss: 1.9403
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3591 - loss: 1.9406
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3589 - loss: 1.9408
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3586 - loss: 1.9410
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3585 - loss: 1.9412
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3583 - loss: 1.9413
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3582 - loss: 1.9416
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3580 - loss: 1.9418
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3578 - loss: 1.9420
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3577 - loss: 1.9423
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3576 - loss: 1.9426
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3574 - loss: 1.9429
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3573 - loss: 1.9431
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3572 - loss: 1.9433
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3570 - loss: 1.9435
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3569 - loss: 1.9437
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3568 - loss: 1.9439
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3567 - loss: 1.9441
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3566 - loss: 1.9443
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3565 - loss: 1.9444
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3565 - loss: 1.9446
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3563 - loss: 1.9448
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3562 - loss: 1.9450
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3561 - loss: 1.9451 - val_accuracy: 0.3135 - val_loss: 2.1500

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 637ms/step
[1m52/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 984us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 9ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:13[0m 855ms/step
[1m 54/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 952us/step  
[1m106/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 963us/step
[1m160/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 953us/step
[1m220/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 922us/step
[1m274/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 925us/step
[1m333/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 913us/step
[1m390/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 908us/step
[1m445/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 909us/step
[1m500/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 911us/step
[1m553/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 914us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m44/86[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 15ms/step
[1m 56/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 924us/step
[1m113/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 905us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 34.58 [%]
Global F1 score (validation) = 32.88 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[1.12003172e-02 1.08146966e-02 1.80994961e-02 ... 3.05937510e-02
  5.37507050e-02 2.78139599e-02]
 [2.47558090e-03 2.97327363e-03 2.90886359e-03 ... 1.42410159e-01
  6.14556763e-03 3.13807977e-03]
 [6.76688796e-04 4.38210904e-04 4.89534694e-04 ... 8.08183011e-03
  8.96019104e-04 2.67261057e-04]
 ...
 [8.46082270e-02 1.19144395e-01 1.58082113e-01 ... 1.25045190e-02
  1.44683748e-01 8.33794698e-02]
 [1.02365091e-01 8.84727985e-02 6.39385432e-02 ... 4.66293469e-02
  5.94674908e-02 3.96306589e-02]
 [1.44085944e-01 5.62813804e-02 1.01801530e-01 ... 5.89524535e-03
  3.21073681e-01 5.48469163e-02]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 39.28 [%]
Global accuracy score (test) = 28.1 [%]
Global F1 score (train) = 38.8 [%]
Global F1 score (test) = 27.1 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.28      0.43      0.34       184
 CAMINAR CON MÓVIL O LIBRO       0.09      0.08      0.09       184
       CAMINAR USUAL SPEED       0.11      0.03      0.05       184
            CAMINAR ZIGZAG       0.22      0.33      0.26       184
          DE PIE BARRIENDO       0.49      0.26      0.34       184
   DE PIE DOBLANDO TOALLAS       0.32      0.26      0.29       184
    DE PIE MOVIENDO LIBROS       0.26      0.26      0.26       184
          DE PIE USANDO PC       0.14      0.12      0.13       184
        FASE REPOSO CON K5       0.39      0.63      0.48       184
INCREMENTAL CICLOERGOMETRO       0.41      0.43      0.42       184
           SENTADO LEYENDO       0.30      0.31      0.30       184
         SENTADO USANDO PC       0.11      0.08      0.09       184
      SENTADO VIENDO LA TV       0.17      0.23      0.20       184
   SUBIR Y BAJAR ESCALERAS       0.34      0.30      0.32       184
                    TROTAR       0.50      0.49      0.50       161

                  accuracy                           0.28      2737
                 macro avg       0.28      0.28      0.27      2737
              weighted avg       0.27      0.28      0.27      2737


Accuracy capturado en la ejecución 24: 28.1 [%]
F1-score capturado en la ejecución 24: 27.1 [%]

=== EJECUCIÓN 25 ===

--- TRAIN (ejecución 25) ---

--- TEST (ejecución 25) ---
2025-11-07 13:27:17.338694: 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`.
2025-11-07 13:27:17.350108: 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 00:00:1762518437.363204 2828332 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762518437.367325 2828332 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762518437.377130 2828332 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518437.377148 2828332 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518437.377151 2828332 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518437.377152 2828332 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:27:17.380298: 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 00:00:1762518439.629521 2828332 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762518442.706127 2828467 service.cc:152] XLA service 0x710a18002ae0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762518442.706162 2828467 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:27:22.785145: 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 00:00:1762518443.204412 2828467 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762518445.740378 2828467 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:06[0m 5s/step - accuracy: 0.0625 - loss: 3.7160
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0589 - loss: 3.3943    
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0643 - loss: 3.3504
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0656 - loss: 3.3333
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0680 - loss: 3.3172
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0704 - loss: 3.3013
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0721 - loss: 3.2863
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0738 - loss: 3.2723
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0756 - loss: 3.2593
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0771 - loss: 3.2484
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0789 - loss: 3.2361
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0807 - loss: 3.2250
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0825 - loss: 3.2138
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0840 - loss: 3.2041
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0855 - loss: 3.1948
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0871 - loss: 3.1853
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0886 - loss: 3.1763
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0898 - loss: 3.1693
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0909 - loss: 3.1624
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0918 - loss: 3.1566
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0929 - loss: 3.1500
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0937 - loss: 3.1447
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0946 - loss: 3.1386
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0955 - loss: 3.1328
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0965 - loss: 3.1270
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0973 - loss: 3.1216
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0982 - loss: 3.1159
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0990 - loss: 3.1107
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0998 - loss: 3.1056
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1006 - loss: 3.1004
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1015 - loss: 3.0953
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1023 - loss: 3.0904
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1031 - loss: 3.0852
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1039 - loss: 3.0807
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1046 - loss: 3.0762
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1053 - loss: 3.0722
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1060 - loss: 3.0676
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1067 - loss: 3.0635
[1m1033/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1074 - loss: 3.0592
[1m1059/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1081 - loss: 3.0552
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1087 - loss: 3.0513
[1m1110/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1093 - loss: 3.0474
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1100 - loss: 3.0431
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1104 - loss: 3.0408
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1105 - loss: 3.0406 - val_accuracy: 0.2519 - val_loss: 2.3024
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.1875 - loss: 2.7721
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1743 - loss: 2.6764  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1794 - loss: 2.6637
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6492
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1846 - loss: 2.6382
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1848 - loss: 2.6326
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1852 - loss: 2.6272
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1857 - loss: 2.6233
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1856 - loss: 2.6207
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1852 - loss: 2.6192
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1848 - loss: 2.6179
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1844 - loss: 2.6165
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1841 - loss: 2.6158
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1838 - loss: 2.6151
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1837 - loss: 2.6147
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.6143
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.6135
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1836 - loss: 2.6129
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1837 - loss: 2.6122
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1838 - loss: 2.6110
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1839 - loss: 2.6098
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1841 - loss: 2.6088
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1842 - loss: 2.6079
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1843 - loss: 2.6070
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1844 - loss: 2.6062
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1846 - loss: 2.6054
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1847 - loss: 2.6046
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1848 - loss: 2.6038
[1m 751/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1850 - loss: 2.6030
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1851 - loss: 2.6021
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1852 - loss: 2.6014
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1854 - loss: 2.6006
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1855 - loss: 2.5998
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1856 - loss: 2.5990
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1858 - loss: 2.5983
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1859 - loss: 2.5975
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1861 - loss: 2.5966
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1862 - loss: 2.5958
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1863 - loss: 2.5950
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1864 - loss: 2.5943
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1865 - loss: 2.5936
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1866 - loss: 2.5930
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1866 - loss: 2.5922
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1867 - loss: 2.5916
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1867 - loss: 2.5915 - val_accuracy: 0.2835 - val_loss: 2.2359
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.0910
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3449  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3785
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3993
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.4104
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2241 - loss: 2.4191
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2228 - loss: 2.4262
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2213 - loss: 2.4343
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2200 - loss: 2.4407
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2190 - loss: 2.4455
[1m 264/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4489
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4512
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2172 - loss: 2.4526
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4537
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4549
[1m 393/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4560
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2160 - loss: 2.4571
[1m 446/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2158 - loss: 2.4579
[1m 474/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2157 - loss: 2.4585
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2157 - loss: 2.4588
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2156 - loss: 2.4590
[1m 554/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2156 - loss: 2.4592
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2155 - loss: 2.4593
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2155 - loss: 2.4593
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2154 - loss: 2.4593
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2153 - loss: 2.4596
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2151 - loss: 2.4598
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2150 - loss: 2.4601
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2149 - loss: 2.4602
[1m 762/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2148 - loss: 2.4603
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2147 - loss: 2.4603
[1m 813/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2146 - loss: 2.4605
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2145 - loss: 2.4606
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2145 - loss: 2.4607
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2144 - loss: 2.4607
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2144 - loss: 2.4608
[1m 945/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2143 - loss: 2.4608
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2143 - loss: 2.4607
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2142 - loss: 2.4607
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2142 - loss: 2.4606
[1m1054/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2142 - loss: 2.4605
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2142 - loss: 2.4603
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2142 - loss: 2.4601
[1m1138/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2142 - loss: 2.4598
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2141 - loss: 2.4597 - val_accuracy: 0.2988 - val_loss: 2.2036
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3968
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1913 - loss: 2.4928  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1980 - loss: 2.4754
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2021 - loss: 2.4597
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2043 - loss: 2.4508
[1m 125/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2060 - loss: 2.4450
[1m 149/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2081 - loss: 2.4404
[1m 175/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2098 - loss: 2.4362
[1m 202/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2108 - loss: 2.4340
[1m 230/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2112 - loss: 2.4326
[1m 260/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2115 - loss: 2.4318
[1m 285/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2118 - loss: 2.4312
[1m 312/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2121 - loss: 2.4304
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2123 - loss: 2.4297
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2125 - loss: 2.4291
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2126 - loss: 2.4286
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2128 - loss: 2.4278
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2130 - loss: 2.4269
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2131 - loss: 2.4261
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2132 - loss: 2.4255
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2134 - loss: 2.4247
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2137 - loss: 2.4237
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2139 - loss: 2.4227
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2142 - loss: 2.4218
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2144 - loss: 2.4207
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2147 - loss: 2.4197
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2150 - loss: 2.4187
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2154 - loss: 2.4178
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2156 - loss: 2.4170
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2159 - loss: 2.4161
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2161 - loss: 2.4154
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4145
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4136
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4127
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4120
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2173 - loss: 2.4112
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2175 - loss: 2.4105
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4097
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4090
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4083
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2181 - loss: 2.4077
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4071
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2183 - loss: 2.4066
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4060
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4058 - val_accuracy: 0.3121 - val_loss: 2.1811
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.5949
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1997 - loss: 2.4662  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2076 - loss: 2.4298
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2104 - loss: 2.4112
[1m 101/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2135 - loss: 2.3968
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2159 - loss: 2.3872
[1m 154/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2172 - loss: 2.3819
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2183 - loss: 2.3784
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2196 - loss: 2.3741
[1m 236/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.3693
[1m 263/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3657
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2231 - loss: 2.3631
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2238 - loss: 2.3607
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2243 - loss: 2.3587
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2247 - loss: 2.3570
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2251 - loss: 2.3556
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2254 - loss: 2.3544
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2257 - loss: 2.3535
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2260 - loss: 2.3524
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2263 - loss: 2.3514
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2266 - loss: 2.3505
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2269 - loss: 2.3496
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2272 - loss: 2.3486
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2274 - loss: 2.3479
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2275 - loss: 2.3473
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2276 - loss: 2.3468
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2277 - loss: 2.3463
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2278 - loss: 2.3460
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3457
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2279 - loss: 2.3454
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2280 - loss: 2.3449
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2281 - loss: 2.3445
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2282 - loss: 2.3441
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2282 - loss: 2.3437
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2283 - loss: 2.3433
[1m 907/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2284 - loss: 2.3429
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3424
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3420
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3414
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2291 - loss: 2.3410
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2293 - loss: 2.3406
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3401
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3397
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2298 - loss: 2.3392
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2300 - loss: 2.3388
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2300 - loss: 2.3387 - val_accuracy: 0.3230 - val_loss: 2.1529
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 1.9240
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2449 - loss: 2.2100  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2240
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2307
[1m 100/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2402
[1m 125/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2503 - loss: 2.2500
[1m 149/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2495 - loss: 2.2559
[1m 173/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2604
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2478 - loss: 2.2638
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2670
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2466 - loss: 2.2697
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2464 - loss: 2.2721
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2461 - loss: 2.2741
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.2757
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2461 - loss: 2.2768
[1m 392/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2777
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2787
[1m 445/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2464 - loss: 2.2792
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2466 - loss: 2.2797
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2801
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2803
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2805
[1m 575/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2808
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2810
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2812
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2814
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2816
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2819
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2822
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2825
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2829
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2832
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2833
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2833
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2834
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2835
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2835
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2835
[1m 993/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2835
[1m1019/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2835
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2834
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2834
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2833
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2833
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2833
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2833 - val_accuracy: 0.3101 - val_loss: 2.1535
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.0985
[1m  30/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2617 - loss: 2.2507  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 2.2566
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2672 - loss: 2.2498
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2682 - loss: 2.2487
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2678 - loss: 2.2505
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2673 - loss: 2.2508
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.2505
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2666 - loss: 2.2501
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2663 - loss: 2.2500
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2658 - loss: 2.2503
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2655 - loss: 2.2500
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2652 - loss: 2.2497
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2648 - loss: 2.2495
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2644 - loss: 2.2494
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2641 - loss: 2.2495
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2638 - loss: 2.2494
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2494
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2494
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2495
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.2495
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2632 - loss: 2.2495
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2495
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2494
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2492
[1m 664/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2490
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2487
[1m 719/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2486
[1m 747/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2484
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2625 - loss: 2.2483
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2624 - loss: 2.2482
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2623 - loss: 2.2480
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2622 - loss: 2.2479
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2621 - loss: 2.2477
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2476
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2475
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2617 - loss: 2.2474
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2472
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2470
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2468
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2467
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2465
[1m1125/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2613 - loss: 2.2464
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2613 - loss: 2.2463
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2613 - loss: 2.2463 - val_accuracy: 0.3302 - val_loss: 2.1207
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.1609
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2648 - loss: 2.2267  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2731 - loss: 2.2105
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2759 - loss: 2.2045
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1998
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1959
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1946
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1944
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1943
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2813 - loss: 2.1947
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1958
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1970
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1983
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1994
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2787 - loss: 2.2005
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2780 - loss: 2.2014
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2774 - loss: 2.2023
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2769 - loss: 2.2031
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2765 - loss: 2.2037
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2761 - loss: 2.2043
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2757 - loss: 2.2047
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2754 - loss: 2.2050
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2750 - loss: 2.2054
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2747 - loss: 2.2056
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2745 - loss: 2.2057
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2742 - loss: 2.2059
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2739 - loss: 2.2061
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2736 - loss: 2.2064
[1m 748/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2733 - loss: 2.2066
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2731 - loss: 2.2068
[1m 803/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2729 - loss: 2.2068
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.2068
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.2068
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2724 - loss: 2.2067
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2723 - loss: 2.2067
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2722 - loss: 2.2067
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.2068
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2719 - loss: 2.2068
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.2068
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2717 - loss: 2.2069
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2716 - loss: 2.2070
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2715 - loss: 2.2071
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2714 - loss: 2.2072
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2713 - loss: 2.2073
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2712 - loss: 2.2074 - val_accuracy: 0.3413 - val_loss: 2.1228
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 2.5959
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2856 - loss: 2.2917  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2924 - loss: 2.2542
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2921 - loss: 2.2451
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2911 - loss: 2.2417
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2907 - loss: 2.2377
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2907 - loss: 2.2331
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2906 - loss: 2.2292
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2903 - loss: 2.2265
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2900 - loss: 2.2240
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2899 - loss: 2.2226
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2897 - loss: 2.2212
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2895 - loss: 2.2201
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.2188
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.2176
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2886 - loss: 2.2167
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2883 - loss: 2.2156
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2881 - loss: 2.2147
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 2.2138
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2876 - loss: 2.2127
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2873 - loss: 2.2117
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2870 - loss: 2.2108
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2867 - loss: 2.2100
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.2093
[1m 637/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2861 - loss: 2.2086
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.2078
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.2069
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 2.2060
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.2052
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.2044
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.2036
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.2030
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.2023
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.2017
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.2011
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.2005
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1999
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1994
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1990
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1985
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1981
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1976
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1971
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1966
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1965 - val_accuracy: 0.3208 - val_loss: 2.1207
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0679
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1898  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1844
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1858
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1885
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1896
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1894
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1892
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1904
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1916
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1927
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2777 - loss: 2.1933
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1936
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1935
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1931
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1928
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1924
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1919
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1912
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1906
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2771 - loss: 2.1899
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1892
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2773 - loss: 2.1885
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1880
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1874
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2775 - loss: 2.1869
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2776 - loss: 2.1863
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1857
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1850
[1m 776/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2780 - loss: 2.1844
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2781 - loss: 2.1838
[1m 829/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1832
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1827
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2786 - loss: 2.1822
[1m 903/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2787 - loss: 2.1817
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2789 - loss: 2.1813
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1808
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2792 - loss: 2.1803
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1798
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2795 - loss: 2.1794
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1789
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1784
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1779
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1775
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1773 - val_accuracy: 0.3286 - val_loss: 2.1244
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m27s[0m 24ms/step - accuracy: 0.1250 - loss: 2.3737
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2718 - loss: 2.1604  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2792 - loss: 2.1321
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1266
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1327
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1374
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1411
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1423
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1443
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1456
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2827 - loss: 2.1462
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1466
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1463
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1455
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1451
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1450
[1m 428/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1449
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1449
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1449
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1449
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1447
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1446
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1444
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2847 - loss: 2.1443
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1441
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2850 - loss: 2.1440
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1437
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1435
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1433
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1430
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1428
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1425
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1422
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1419
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1417
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2864 - loss: 2.1414
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1412
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2867 - loss: 2.1409
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1407
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1404
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1403
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2872 - loss: 2.1402
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1401
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2874 - loss: 2.1401
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2874 - loss: 2.1400 - val_accuracy: 0.3335 - val_loss: 2.0980
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.2253
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1603  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2902 - loss: 2.1396
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2881 - loss: 2.1450
[1m 100/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1452
[1m 127/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1436
[1m 153/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1417
[1m 178/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1413
[1m 207/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1401
[1m 233/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1391
[1m 260/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1391
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1391
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1389
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1386
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1385
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1383
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1378
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1375
[1m 479/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2899 - loss: 2.1372
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2902 - loss: 2.1366
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2906 - loss: 2.1359
[1m 561/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2909 - loss: 2.1352
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2912 - loss: 2.1344
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1338
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2916 - loss: 2.1332
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1327
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1322
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1318
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1313
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1308
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2927 - loss: 2.1303
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2929 - loss: 2.1298
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1293
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1288
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2931 - loss: 2.1284
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1281
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1279
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2933 - loss: 2.1276
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1274
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1272
[1m1076/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2936 - loss: 2.1270
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2937 - loss: 2.1269
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2938 - loss: 2.1267
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2939 - loss: 2.1266 - val_accuracy: 0.3252 - val_loss: 2.1305
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.4375 - loss: 1.9137
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3360 - loss: 2.0771  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0946
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3192 - loss: 2.1030
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3156 - loss: 2.1056
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.1060
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.1065
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.1068
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3093 - loss: 2.1072
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3084 - loss: 2.1075
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3078 - loss: 2.1074
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3076 - loss: 2.1065
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3078 - loss: 2.1051
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3078 - loss: 2.1043
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.1038
[1m 399/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3075 - loss: 2.1035
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3073 - loss: 2.1033
[1m 453/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3072 - loss: 2.1029
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.1024
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.1021
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.1016
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.1014
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.1011
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.1006
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.1003
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.1001
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0999
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0997
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0997
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0997
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0997
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0997
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0996
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0995
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0993
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0993
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0992
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0991
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0990
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0989
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0988
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0987
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0985
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0985
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0984 - val_accuracy: 0.3252 - val_loss: 2.1195
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.1884
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3173 - loss: 2.0531  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0321
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0360
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3176 - loss: 2.0424
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3158 - loss: 2.0463
[1m 158/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3154 - loss: 2.0471
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3152 - loss: 2.0480
[1m 208/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3148 - loss: 2.0488
[1m 234/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0491
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0501
[1m 288/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0510
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0517
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0523
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0532
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0546
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0556
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0564
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0571
[1m 501/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0579
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0584
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0588
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0591
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0592
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0592
[1m 654/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0592
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0594
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0595
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0597
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0599
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0602
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0606
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0609
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0613
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0616
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0620
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0623
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0627
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0630
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0633
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0637
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0639
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0641
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0644
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0645 - val_accuracy: 0.3313 - val_loss: 2.1284
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m31s[0m 27ms/step - accuracy: 0.4375 - loss: 2.0194
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3497 - loss: 2.0715  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3382 - loss: 2.0746
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3328 - loss: 2.0675
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 2.0675
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3279 - loss: 2.0669
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3257 - loss: 2.0666
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3241 - loss: 2.0663
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0660
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0659
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0663
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0666
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0667
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3189 - loss: 2.0666
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3182 - loss: 2.0663
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3177 - loss: 2.0661
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0660
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0659
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3163 - loss: 2.0660
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3160 - loss: 2.0660
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3157 - loss: 2.0659
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0657
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0656
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3151 - loss: 2.0656
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0656
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3147 - loss: 2.0656
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0655
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0655
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0655
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0656
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3137 - loss: 2.0656
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0657
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3133 - loss: 2.0658
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0659
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3130 - loss: 2.0659
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0659
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0658
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0656
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0654
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0652
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0651
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0650
[1m1140/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0649
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0648 - val_accuracy: 0.3311 - val_loss: 2.1191
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.2938
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2811 - loss: 2.1052  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2957 - loss: 2.0947
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2955 - loss: 2.0975
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2967 - loss: 2.0956
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2989 - loss: 2.0904
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.0845
[1m 184/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0810
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0783
[1m 234/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0758
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 2.0731
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.0708
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3045 - loss: 2.0686
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3049 - loss: 2.0671
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0651
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0638
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0628
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0619
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0610
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0602
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0594
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0588
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3073 - loss: 2.0584
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3076 - loss: 2.0580
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3079 - loss: 2.0576
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3081 - loss: 2.0573
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0568
[1m 726/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0564
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0559
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0555
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0551
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0549
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0545
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3100 - loss: 2.0541
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0538
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0534
[1m 966/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0531
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0527
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0522
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0518
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0513
[1m1096/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0509
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0505
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0501
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0500 - val_accuracy: 0.3351 - val_loss: 2.1178

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 643ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 950us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:24[0m 875ms/step
[1m 54/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 949us/step  
[1m109/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 929us/step
[1m166/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 913us/step
[1m219/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 920us/step
[1m274/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 921us/step
[1m324/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 935us/step
[1m380/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 931us/step
[1m431/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 938us/step
[1m491/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 926us/step
[1m547/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 923us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 50/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m109/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 938us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 31.31 [%]
Global F1 score (validation) = 29.81 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.02714615 0.00817617 0.01571951 ... 0.02307475 0.05572835 0.02107826]
 [0.00111191 0.0011585  0.00090453 ... 0.1603873  0.00606685 0.00266327]
 [0.00439524 0.00072872 0.00055449 ... 0.00439133 0.00137309 0.0012355 ]
 ...
 [0.17124757 0.05470803 0.15066206 ... 0.00834253 0.15724441 0.15566266]
 [0.13789208 0.0568222  0.12384544 ... 0.00600428 0.1193059  0.1324261 ]
 [0.16277581 0.04956075 0.11607824 ... 0.00803821 0.13417396 0.1024019 ]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 41.67 [%]
Global accuracy score (test) = 30.03 [%]
Global F1 score (train) = 40.59 [%]
Global F1 score (test) = 28.87 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.33      0.62      0.43       184
 CAMINAR CON MÓVIL O LIBRO       0.29      0.26      0.28       184
       CAMINAR USUAL SPEED       0.15      0.07      0.09       184
            CAMINAR ZIGZAG       0.26      0.28      0.27       184
          DE PIE BARRIENDO       0.48      0.27      0.35       184
   DE PIE DOBLANDO TOALLAS       0.28      0.42      0.34       184
    DE PIE MOVIENDO LIBROS       0.18      0.15      0.17       184
          DE PIE USANDO PC       0.10      0.13      0.11       184
        FASE REPOSO CON K5       0.40      0.66      0.50       184
INCREMENTAL CICLOERGOMETRO       0.59      0.43      0.50       184
           SENTADO LEYENDO       0.22      0.13      0.16       184
         SENTADO USANDO PC       0.27      0.02      0.03       184
      SENTADO VIENDO LA TV       0.16      0.32      0.21       184
   SUBIR Y BAJAR ESCALERAS       0.33      0.24      0.28       184
                    TROTAR       0.74      0.53      0.62       161

                  accuracy                           0.30      2737
                 macro avg       0.32      0.30      0.29      2737
              weighted avg       0.32      0.30      0.29      2737


Accuracy capturado en la ejecución 25: 30.03 [%]
F1-score capturado en la ejecución 25: 28.87 [%]

=== EJECUCIÓN 26 ===

--- TRAIN (ejecución 26) ---

--- TEST (ejecución 26) ---
2025-11-07 13:28:24.316835: 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`.
2025-11-07 13:28:24.328412: 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 00:00:1762518504.341628 2831190 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762518504.345818 2831190 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762518504.355630 2831190 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518504.355650 2831190 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518504.355652 2831190 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518504.355653 2831190 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:28:24.358875: 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 00:00:1762518506.632315 2831190 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762518509.723436 2831301 service.cc:152] XLA service 0x7ddb50031460 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762518509.723472 2831301 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:28:29.788339: 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 00:00:1762518510.229880 2831301 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762518512.778950 2831301 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:45:10[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.1514
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0479 - loss: 3.2492        
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0611 - loss: 3.2570
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0672 - loss: 3.2673
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0717 - loss: 3.2652
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0748 - loss: 3.2599
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0778 - loss: 3.2530
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0801 - loss: 3.2457
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0821 - loss: 3.2388
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0841 - loss: 3.2326
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0859 - loss: 3.2270
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0874 - loss: 3.2220
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0891 - loss: 3.2156
[1m 348/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0905 - loss: 3.2094
[1m 377/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0919 - loss: 3.2024
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0931 - loss: 3.1966
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0944 - loss: 3.1903
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0957 - loss: 3.1837
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0969 - loss: 3.1775
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0980 - loss: 3.1715
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0992 - loss: 3.1653
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1001 - loss: 3.1599
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1012 - loss: 3.1542
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1021 - loss: 3.1491
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1030 - loss: 3.1435
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1040 - loss: 3.1381
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1049 - loss: 3.1330
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1058 - loss: 3.1276
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1067 - loss: 3.1224
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1075 - loss: 3.1174
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1083 - loss: 3.1124
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1091 - loss: 3.1076
[1m 873/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1099 - loss: 3.1025
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1106 - loss: 3.0981
[1m 928/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1114 - loss: 3.0936
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1121 - loss: 3.0890
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1128 - loss: 3.0845
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1135 - loss: 3.0803
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1142 - loss: 3.0763
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1148 - loss: 3.0722
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1155 - loss: 3.0679
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1161 - loss: 3.0641
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1167 - loss: 3.0602
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1167 - loss: 3.0600
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1168 - loss: 3.0599 - val_accuracy: 0.2277 - val_loss: 2.3807
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.5486
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1734 - loss: 2.6685  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1735 - loss: 2.6748
[1m  76/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1753 - loss: 2.6748
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1763 - loss: 2.6782
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1773 - loss: 2.6759
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1785 - loss: 2.6704
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.6674
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1785 - loss: 2.6649
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1787 - loss: 2.6628
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1785 - loss: 2.6618
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1784 - loss: 2.6607
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1783 - loss: 2.6593
[1m 345/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1783 - loss: 2.6579
[1m 373/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1782 - loss: 2.6568
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6557
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6548
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6539
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6529
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1778 - loss: 2.6521
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1777 - loss: 2.6514
[1m 563/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1777 - loss: 2.6506
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1777 - loss: 2.6496
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1777 - loss: 2.6487
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1778 - loss: 2.6478
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6467
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1779 - loss: 2.6457
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1780 - loss: 2.6446
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1781 - loss: 2.6434
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1782 - loss: 2.6423
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1783 - loss: 2.6412
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1784 - loss: 2.6401
[1m 860/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1785 - loss: 2.6389
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1787 - loss: 2.6379
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1788 - loss: 2.6369
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1790 - loss: 2.6359
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1791 - loss: 2.6349
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1792 - loss: 2.6339
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1794 - loss: 2.6330
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1795 - loss: 2.6320
[1m1075/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1796 - loss: 2.6311
[1m1103/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1797 - loss: 2.6303
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1798 - loss: 2.6294
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1799 - loss: 2.6286 - val_accuracy: 0.2523 - val_loss: 2.2678
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.5193
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1783 - loss: 2.5383  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1900 - loss: 2.5356
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1979 - loss: 2.5241
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2001 - loss: 2.5225
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2011 - loss: 2.5223
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2013 - loss: 2.5228
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2017 - loss: 2.5223
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2018 - loss: 2.5220
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2019 - loss: 2.5210
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2019 - loss: 2.5201
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2019 - loss: 2.5200
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2017 - loss: 2.5201
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2015 - loss: 2.5200
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2014 - loss: 2.5200
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2012 - loss: 2.5199
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2012 - loss: 2.5200
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2011 - loss: 2.5198
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2011 - loss: 2.5196
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.5193
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.5190
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.5185
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.5180
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2010 - loss: 2.5177
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.5174
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.5172
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.5168
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2010 - loss: 2.5163
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.5158
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2011 - loss: 2.5152
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2012 - loss: 2.5145
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2013 - loss: 2.5138
[1m 862/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2013 - loss: 2.5132
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2014 - loss: 2.5125
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2015 - loss: 2.5120
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2015 - loss: 2.5113
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2016 - loss: 2.5108
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2016 - loss: 2.5102
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2017 - loss: 2.5098
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2018 - loss: 2.5092
[1m1076/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2019 - loss: 2.5087
[1m1103/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2020 - loss: 2.5082
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2021 - loss: 2.5076
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step - accuracy: 0.2021 - loss: 2.5072
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2021 - loss: 2.5072 - val_accuracy: 0.2656 - val_loss: 2.2184
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1250 - loss: 2.4715
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2531 - loss: 2.3480  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2458 - loss: 2.3597
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2386 - loss: 2.3688
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2347 - loss: 2.3719
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2313 - loss: 2.3753
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3794
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2259 - loss: 2.3859
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2242 - loss: 2.3900
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2231 - loss: 2.3931
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2220 - loss: 2.3959
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2210 - loss: 2.3983
[1m 318/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2204 - loss: 2.3997
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2199 - loss: 2.4004
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2195 - loss: 2.4012
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2190 - loss: 2.4020
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2187 - loss: 2.4026
[1m 450/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4033
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4039
[1m 503/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2180 - loss: 2.4044
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2177 - loss: 2.4049
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2176 - loss: 2.4054
[1m 583/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2174 - loss: 2.4059
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2172 - loss: 2.4063
[1m 638/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2170 - loss: 2.4067
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2169 - loss: 2.4070
[1m 692/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2168 - loss: 2.4073
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4076
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4077
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4079
[1m 799/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4080
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4080
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4078
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4077
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4076
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4075
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2164 - loss: 2.4075
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4074
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4074
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4074
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4074
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4073
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2165 - loss: 2.4072
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4071
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2166 - loss: 2.4070 - val_accuracy: 0.2855 - val_loss: 2.1826
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.1697
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3427  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2347 - loss: 2.3418
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3502
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2361 - loss: 2.3534
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2351 - loss: 2.3559
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2346 - loss: 2.3564
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3556
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2339 - loss: 2.3552
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3540
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3531
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2331 - loss: 2.3520
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2330 - loss: 2.3511
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3505
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3503
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3502
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2331 - loss: 2.3499
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3497
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3497
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3496
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3498
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2333 - loss: 2.3498
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3498
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3496
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2335 - loss: 2.3495
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3494
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2337 - loss: 2.3492
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3489
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2339 - loss: 2.3487
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.3484
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3482
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2341 - loss: 2.3479
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3477
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3475
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3473
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3471
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3469
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3468
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3467
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3465
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3464
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3462
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2344 - loss: 2.3461
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2345 - loss: 2.3460 - val_accuracy: 0.3115 - val_loss: 2.1604
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.5692
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2385 - loss: 2.2930  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2343 - loss: 2.3175
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2302 - loss: 2.3317
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2268 - loss: 2.3386
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2250 - loss: 2.3414
[1m 169/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2240 - loss: 2.3438
[1m 198/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2236 - loss: 2.3444
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2240 - loss: 2.3429
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2245 - loss: 2.3422
[1m 281/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2250 - loss: 2.3414
[1m 311/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2255 - loss: 2.3402
[1m 338/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2260 - loss: 2.3393
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2264 - loss: 2.3386
[1m 395/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2271 - loss: 2.3375
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2276 - loss: 2.3364
[1m 451/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2282 - loss: 2.3353
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3343
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2293 - loss: 2.3332
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2298 - loss: 2.3321
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2302 - loss: 2.3312
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2307 - loss: 2.3303
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2310 - loss: 2.3294
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2314 - loss: 2.3285
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3277
[1m 695/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2320 - loss: 2.3268
[1m 722/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2323 - loss: 2.3260
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2326 - loss: 2.3252
[1m 777/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2329 - loss: 2.3245
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2332 - loss: 2.3238
[1m 830/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2334 - loss: 2.3233
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2336 - loss: 2.3227
[1m 887/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2338 - loss: 2.3221
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2340 - loss: 2.3216
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2342 - loss: 2.3210
[1m 972/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2345 - loss: 2.3204
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2347 - loss: 2.3198
[1m1031/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3192
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2352 - loss: 2.3186
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2354 - loss: 2.3181
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3176
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2358 - loss: 2.3171
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2359 - loss: 2.3168 - val_accuracy: 0.3167 - val_loss: 2.1376
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1464
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2103 - loss: 2.3313  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2244 - loss: 2.3078
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2324 - loss: 2.2964
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2391 - loss: 2.2880
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2425 - loss: 2.2811
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2446 - loss: 2.2764
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2458 - loss: 2.2746
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2466 - loss: 2.2732
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2734
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2475 - loss: 2.2734
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2481 - loss: 2.2730
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2727
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2489 - loss: 2.2727
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2728
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2494 - loss: 2.2730
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.2732
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2732
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2497 - loss: 2.2732
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2732
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2729
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2501 - loss: 2.2726
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.2723
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2504 - loss: 2.2719
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2505 - loss: 2.2716
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2506 - loss: 2.2713
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2711
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2508 - loss: 2.2708
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2510 - loss: 2.2705
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2511 - loss: 2.2702
[1m 809/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2699
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2696
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2514 - loss: 2.2693
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2515 - loss: 2.2691
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2516 - loss: 2.2688
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2517 - loss: 2.2685
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2518 - loss: 2.2683
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2519 - loss: 2.2681
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2519 - loss: 2.2680
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2520 - loss: 2.2678
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2521 - loss: 2.2677
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2522 - loss: 2.2676
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2522 - loss: 2.2675
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2523 - loss: 2.2673 - val_accuracy: 0.3286 - val_loss: 2.1211
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2314
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2363 - loss: 2.2567  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2476 - loss: 2.2584
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2505 - loss: 2.2496
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2522 - loss: 2.2436
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2523 - loss: 2.2444
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2529 - loss: 2.2443
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2442
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2536 - loss: 2.2438
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2538 - loss: 2.2429
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2417
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2403
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2393
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2385
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2375
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2370
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2556 - loss: 2.2364
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2357
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2351
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2346
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2339
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2565 - loss: 2.2333
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2567 - loss: 2.2327
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2570 - loss: 2.2320
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2573 - loss: 2.2313
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2576 - loss: 2.2307
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2579 - loss: 2.2299
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2583 - loss: 2.2294
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2585 - loss: 2.2289
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2286
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2589 - loss: 2.2284
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2591 - loss: 2.2281
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2280
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2594 - loss: 2.2279
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2596 - loss: 2.2278
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2597 - loss: 2.2276
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2274
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2273
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2601 - loss: 2.2271
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2602 - loss: 2.2270
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2268
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2266
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2265
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2264 - val_accuracy: 0.3294 - val_loss: 2.1166
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.4229
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2791 - loss: 2.2220  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2769 - loss: 2.2138
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2781 - loss: 2.2053
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2794 - loss: 2.2011
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2798 - loss: 2.1977
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2786 - loss: 2.1989
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2768 - loss: 2.2007
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2753 - loss: 2.2018
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2743 - loss: 2.2027
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2735 - loss: 2.2039
[1m 306/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2733 - loss: 2.2043
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2733 - loss: 2.2043
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2733 - loss: 2.2046
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.2049
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.2052
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.2052
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.2048
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2736 - loss: 2.2044
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2737 - loss: 2.2039
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2738 - loss: 2.2034
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2739 - loss: 2.2031
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2028
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2025
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.2021
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.2018
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.2016
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.2014
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.2013
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2741 - loss: 2.2012
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2011
[1m 858/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2010
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2008
[1m 916/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2007
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2005
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2003
[1m1002/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.2001
[1m1030/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.1999
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.1997
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.1995
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.1993
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2740 - loss: 2.1991
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1990 - val_accuracy: 0.3278 - val_loss: 2.1013
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.9263
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3549 - loss: 1.9804  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3322 - loss: 2.0595
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3228 - loss: 2.0907
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3162 - loss: 2.1080
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 2.1201
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3075 - loss: 2.1296
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3041 - loss: 2.1361
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1405
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2988 - loss: 2.1439
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 2.1466
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1490
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1504
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1515
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1527
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2903 - loss: 2.1541
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1553
[1m 460/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1563
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1575
[1m 517/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1587
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2872 - loss: 2.1595
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1604
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1611
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1616
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1621
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1627
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1632
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1637
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1642
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1647
[1m 818/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1651
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1655
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1660
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1664
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1668
[1m 961/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1671
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1674
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2814 - loss: 2.1677
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1679
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2810 - loss: 2.1681
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2809 - loss: 2.1683
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2808 - loss: 2.1684
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1685
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2807 - loss: 2.1686 - val_accuracy: 0.3141 - val_loss: 2.1294
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.2025
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3333 - loss: 2.1201  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3067 - loss: 2.1584
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2966 - loss: 2.1694
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2930 - loss: 2.1714
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2907 - loss: 2.1720
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1725
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1727
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1716
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1703
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1693
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2875 - loss: 2.1688
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1681
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1674
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1668
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1663
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1659
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1657
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1655
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1652
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2846 - loss: 2.1649
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2845 - loss: 2.1644
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1641
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2843 - loss: 2.1637
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1634
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1631
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1629
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1626
[1m 754/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1623
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1621
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1618
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1615
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1612
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1609
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1607
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1605
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1604
[1m 990/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1603
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1602
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1600
[1m1074/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1598
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1596
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1594
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1591
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1591 - val_accuracy: 0.3194 - val_loss: 2.1206
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2167
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1912  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1715
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1568
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1511
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1494
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2871 - loss: 2.1490
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1461
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1453
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1454
[1m 270/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2883 - loss: 2.1453
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1449
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1444
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1437
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1431
[1m 411/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1426
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2899 - loss: 2.1423
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2903 - loss: 2.1418
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2906 - loss: 2.1413
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2909 - loss: 2.1405
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2912 - loss: 2.1398
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2915 - loss: 2.1391
[1m 603/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2917 - loss: 2.1385
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2918 - loss: 2.1381
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1378
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1374
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1372
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1370
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1369
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1367
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1365
[1m 851/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1363
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2923 - loss: 2.1360
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1358
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1355
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2924 - loss: 2.1352
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1349
[1m1017/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1346
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1344
[1m1068/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1342
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1339
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1337
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1335 - val_accuracy: 0.3178 - val_loss: 2.1505
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.3785
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2311  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2762 - loss: 2.1863
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1627
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2941 - loss: 2.1463
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1341
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3026 - loss: 2.1258
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.1207
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3071 - loss: 2.1171
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3086 - loss: 2.1148
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 2.1134
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 2.1127
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.1119
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.1107
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 2.1100
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 2.1095
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.1089
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.1085
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.1080
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3115 - loss: 2.1077
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3114 - loss: 2.1074
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 2.1071
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3112 - loss: 2.1069
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.1067
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3109 - loss: 2.1064
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3107 - loss: 2.1062
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3106 - loss: 2.1060
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3104 - loss: 2.1059
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3103 - loss: 2.1058
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3101 - loss: 2.1057
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 2.1057
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3097 - loss: 2.1057
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3095 - loss: 2.1058
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.1059
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 2.1060
[1m 970/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3090 - loss: 2.1061
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 2.1061
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 2.1063
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3085 - loss: 2.1064
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3083 - loss: 2.1064
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3082 - loss: 2.1065
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3081 - loss: 2.1066
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3080 - loss: 2.1066 - val_accuracy: 0.3220 - val_loss: 2.1452
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.3125 - loss: 2.2149
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0675  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0921
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0941
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0924
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0920
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3033 - loss: 2.0902
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3040 - loss: 2.0893
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3043 - loss: 2.0880
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0870
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0869
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0877
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3054 - loss: 2.0884
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3058 - loss: 2.0887
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0891
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0893
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0899
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3061 - loss: 2.0905
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0910
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0913
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0917
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3063 - loss: 2.0922
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0926
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0931
[1m 651/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0936
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0940
[1m 708/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0943
[1m 733/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0945
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0947
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0949
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0949
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0950
[1m 863/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3065 - loss: 2.0950
[1m 892/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0950
[1m 919/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3066 - loss: 2.0950
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3067 - loss: 2.0950
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3067 - loss: 2.0948
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3068 - loss: 2.0947
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0946
[1m1053/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0945
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0944
[1m1103/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0943
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3071 - loss: 2.0942
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3072 - loss: 2.0941 - val_accuracy: 0.3355 - val_loss: 2.1218

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 644ms/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:02[0m 836ms/step
[1m 52/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 988us/step  
[1m105/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 969us/step
[1m162/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 940us/step
[1m220/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 921us/step
[1m277/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 914us/step
[1m333/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 911us/step
[1m390/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 908us/step
[1m437/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 925us/step
[1m493/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 922us/step
[1m544/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 929us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 17ms/step
[1m 48/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step 
[1m102/158[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 1ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 33.51 [%]
Global F1 score (validation) = 32.08 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.02297513 0.0229355  0.01593781 ... 0.03456656 0.05489623 0.01194464]
 [0.00341386 0.00408651 0.0014252  ... 0.14445642 0.01014277 0.00670892]
 [0.00173877 0.0005923  0.00078954 ... 0.00593104 0.00120459 0.00125531]
 ...
 [0.17266849 0.08587215 0.12763664 ... 0.01647804 0.14032231 0.07559498]
 [0.17437507 0.07774555 0.1449175  ... 0.01366176 0.14215294 0.09278735]
 [0.21755011 0.07721745 0.09884086 ... 0.03083131 0.10966873 0.06642871]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 38.23 [%]
Global accuracy score (test) = 26.31 [%]
Global F1 score (train) = 37.34 [%]
Global F1 score (test) = 25.23 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.25      0.63      0.36       184
 CAMINAR CON MÓVIL O LIBRO       0.12      0.13      0.12       184
       CAMINAR USUAL SPEED       0.27      0.16      0.20       184
            CAMINAR ZIGZAG       0.24      0.04      0.07       184
          DE PIE BARRIENDO       0.35      0.19      0.25       184
   DE PIE DOBLANDO TOALLAS       0.31      0.26      0.28       184
    DE PIE MOVIENDO LIBROS       0.17      0.13      0.15       184
          DE PIE USANDO PC       0.13      0.22      0.16       184
        FASE REPOSO CON K5       0.56      0.53      0.55       184
INCREMENTAL CICLOERGOMETRO       0.50      0.38      0.43       184
           SENTADO LEYENDO       0.19      0.18      0.19       184
         SENTADO USANDO PC       0.02      0.01      0.01       184
      SENTADO VIENDO LA TV       0.20      0.38      0.26       184
   SUBIR Y BAJAR ESCALERAS       0.21      0.21      0.21       184
                    TROTAR       0.55      0.53      0.54       161

                  accuracy                           0.26      2737
                 macro avg       0.27      0.27      0.25      2737
              weighted avg       0.27      0.26      0.25      2737


Accuracy capturado en la ejecución 26: 26.31 [%]
F1-score capturado en la ejecución 26: 25.23 [%]

=== EJECUCIÓN 27 ===

--- TRAIN (ejecución 27) ---

--- TEST (ejecución 27) ---
2025-11-07 13:29:25.441777: 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`.
2025-11-07 13:29:25.453027: 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 00:00:1762518565.466264 2833801 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762518565.470619 2833801 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762518565.480594 2833801 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518565.480614 2833801 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518565.480616 2833801 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518565.480617 2833801 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:29:25.483795: 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 00:00:1762518567.769783 2833801 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762518570.790267 2833909 service.cc:152] XLA service 0x72421c007930 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762518570.790322 2833909 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:29:30.855782: 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 00:00:1762518571.274225 2833909 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762518573.798029 2833909 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:42:36[0m 5s/step - accuracy: 0.1875 - loss: 3.2151
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0811 - loss: 3.3054    
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0780 - loss: 3.2991
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0769 - loss: 3.2908
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0759 - loss: 3.2861
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0755 - loss: 3.2771
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0754 - loss: 3.2705
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0756 - loss: 3.2636
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0763 - loss: 3.2543
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0776 - loss: 3.2434
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0788 - loss: 3.2338
[1m 299/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0799 - loss: 3.2253
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0810 - loss: 3.2168
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0821 - loss: 3.2094
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0833 - loss: 3.2014
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0842 - loss: 3.1945
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0852 - loss: 3.1879
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0862 - loss: 3.1811
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0871 - loss: 3.1749
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0881 - loss: 3.1688
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0891 - loss: 3.1620
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0900 - loss: 3.1563
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0909 - loss: 3.1503
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0918 - loss: 3.1446
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0927 - loss: 3.1387
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0935 - loss: 3.1339
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0943 - loss: 3.1285
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0951 - loss: 3.1237
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0960 - loss: 3.1183
[1m 783/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0968 - loss: 3.1134
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0977 - loss: 3.1084
[1m 840/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0985 - loss: 3.1034
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0994 - loss: 3.0984
[1m 897/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1002 - loss: 3.0937
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1010 - loss: 3.0891
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1017 - loss: 3.0847
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1025 - loss: 3.0799
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1032 - loss: 3.0757
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1039 - loss: 3.0715
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1046 - loss: 3.0676
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1053 - loss: 3.0633
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1060 - loss: 3.0593
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1067 - loss: 3.0553
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1069 - loss: 3.0542
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1069 - loss: 3.0540 - val_accuracy: 0.2462 - val_loss: 2.3538
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 2.6292
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1916 - loss: 2.6741  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1838 - loss: 2.6717
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1836 - loss: 2.6625
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1843 - loss: 2.6572
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1847 - loss: 2.6557
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1846 - loss: 2.6576
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1843 - loss: 2.6585
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1841 - loss: 2.6580
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1838 - loss: 2.6579
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1835 - loss: 2.6582
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1833 - loss: 2.6583
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1831 - loss: 2.6582
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1830 - loss: 2.6581
[1m 374/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.6580
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1829 - loss: 2.6580
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1828 - loss: 2.6579
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6577
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6574
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1824 - loss: 2.6571
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6570
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1822 - loss: 2.6566
[1m 595/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1822 - loss: 2.6560
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1821 - loss: 2.6553
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1822 - loss: 2.6545
[1m 676/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1822 - loss: 2.6537
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1822 - loss: 2.6528
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6520
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1823 - loss: 2.6511
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1824 - loss: 2.6501
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1825 - loss: 2.6491
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1825 - loss: 2.6482
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6472
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6464
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1826 - loss: 2.6455
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1827 - loss: 2.6446
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.6437
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1828 - loss: 2.6426
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1829 - loss: 2.6416
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1830 - loss: 2.6406
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1831 - loss: 2.6397
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1832 - loss: 2.6387
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1833 - loss: 2.6378
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1834 - loss: 2.6375 - val_accuracy: 0.2857 - val_loss: 2.2556
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.5763
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2394 - loss: 2.4183  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2386 - loss: 2.4277
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2342 - loss: 2.4408
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2295 - loss: 2.4532
[1m 144/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2265 - loss: 2.4597
[1m 172/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2243 - loss: 2.4656
[1m 201/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2222 - loss: 2.4700
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2204 - loss: 2.4733
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2188 - loss: 2.4759
[1m 284/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2173 - loss: 2.4779
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2161 - loss: 2.4797
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2151 - loss: 2.4809
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2144 - loss: 2.4817
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2139 - loss: 2.4823
[1m 425/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2136 - loss: 2.4827
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2131 - loss: 2.4832
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2127 - loss: 2.4839
[1m 507/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2123 - loss: 2.4845
[1m 534/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2121 - loss: 2.4847
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2119 - loss: 2.4847
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2118 - loss: 2.4848
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2116 - loss: 2.4848
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2114 - loss: 2.4850
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2113 - loss: 2.4850
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2112 - loss: 2.4850
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2111 - loss: 2.4849
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2109 - loss: 2.4849
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2108 - loss: 2.4848
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2107 - loss: 2.4847
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2106 - loss: 2.4846
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2105 - loss: 2.4845
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2104 - loss: 2.4842
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2103 - loss: 2.4840
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2103 - loss: 2.4839
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2102 - loss: 2.4837
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2102 - loss: 2.4836
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2101 - loss: 2.4835
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2100 - loss: 2.4833
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2100 - loss: 2.4831
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2100 - loss: 2.4828
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2100 - loss: 2.4825
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2100 - loss: 2.4824 - val_accuracy: 0.2916 - val_loss: 2.2082
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.2842
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2224 - loss: 2.4344  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2242 - loss: 2.4454
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2235 - loss: 2.4450
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2220 - loss: 2.4460
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2217 - loss: 2.4444
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2213 - loss: 2.4426
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4397
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2214 - loss: 2.4373
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2215 - loss: 2.4348
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2216 - loss: 2.4332
[1m 308/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2214 - loss: 2.4322
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4314
[1m 365/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2213 - loss: 2.4305
[1m 394/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2213 - loss: 2.4295
[1m 422/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4288
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4284
[1m 475/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4281
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4278
[1m 532/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2211 - loss: 2.4273
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2211 - loss: 2.4268
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2210 - loss: 2.4265
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2210 - loss: 2.4264
[1m 634/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2210 - loss: 2.4261
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2210 - loss: 2.4258
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2211 - loss: 2.4254
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2211 - loss: 2.4250
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2211 - loss: 2.4247
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2211 - loss: 2.4243
[1m 796/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2211 - loss: 2.4239
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4234
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4230
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4226
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4222
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4218
[1m 956/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4215
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4211
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2213 - loss: 2.4208
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2213 - loss: 2.4204
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2213 - loss: 2.4200
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2214 - loss: 2.4196
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2214 - loss: 2.4191
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2215 - loss: 2.4186
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2215 - loss: 2.4184 - val_accuracy: 0.3040 - val_loss: 2.1560
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1875 - loss: 2.6531
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2385 - loss: 2.3323  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2366 - loss: 2.3322
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3403
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2308 - loss: 2.3450
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2303 - loss: 2.3479
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2301 - loss: 2.3505
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2296 - loss: 2.3538
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2292 - loss: 2.3563
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3577
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3586
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3592
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3592
[1m 362/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3594
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3594
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2289 - loss: 2.3593
[1m 441/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3594
[1m 467/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3596
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3596
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3596
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3595
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3594
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2286 - loss: 2.3593
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2288 - loss: 2.3591
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3586
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2293 - loss: 2.3582
[1m 718/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2295 - loss: 2.3576
[1m 746/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2297 - loss: 2.3572
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2299 - loss: 2.3567
[1m 800/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2301 - loss: 2.3563
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2302 - loss: 2.3559
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2304 - loss: 2.3555
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2305 - loss: 2.3552
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2307 - loss: 2.3548
[1m 940/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2308 - loss: 2.3545
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2310 - loss: 2.3542
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2311 - loss: 2.3538
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2313 - loss: 2.3535
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2314 - loss: 2.3532
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2316 - loss: 2.3528
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2317 - loss: 2.3525
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2318 - loss: 2.3522
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3520 - val_accuracy: 0.3290 - val_loss: 2.1512
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.2500 - loss: 1.8552
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2439 - loss: 2.2270  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2420 - loss: 2.2658
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2424 - loss: 2.2774
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2419 - loss: 2.2835
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2418 - loss: 2.2878
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2896
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.2930
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2430 - loss: 2.2958
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2430 - loss: 2.2983
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2998
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3017
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2424 - loss: 2.3028
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2424 - loss: 2.3038
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2424 - loss: 2.3044
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3049
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2425 - loss: 2.3052
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2427 - loss: 2.3052
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2428 - loss: 2.3051
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2430 - loss: 2.3048
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2431 - loss: 2.3043
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2433 - loss: 2.3037
[1m 589/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2435 - loss: 2.3031
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2437 - loss: 2.3024
[1m 644/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2439 - loss: 2.3017
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2440 - loss: 2.3012
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2442 - loss: 2.3006
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2444 - loss: 2.3000
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2446 - loss: 2.2994
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2448 - loss: 2.2989
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2450 - loss: 2.2985
[1m 833/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2451 - loss: 2.2981
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2453 - loss: 2.2978
[1m 891/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2455 - loss: 2.2974
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2457 - loss: 2.2970
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2459 - loss: 2.2966
[1m 975/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2461 - loss: 2.2962
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2958
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.2953
[1m1056/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2466 - loss: 2.2949
[1m1082/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.2945
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2942
[1m1132/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2471 - loss: 2.2939
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2937
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2937 - val_accuracy: 0.3337 - val_loss: 2.1302
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2500 - loss: 2.3646
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2918 - loss: 2.2339  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2800 - loss: 2.2522
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2752 - loss: 2.2557
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2733 - loss: 2.2545
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2723 - loss: 2.2525
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2713 - loss: 2.2522
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2524
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2697 - loss: 2.2511
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2511
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2682 - loss: 2.2513
[1m 292/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2676 - loss: 2.2516
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2670 - loss: 2.2517
[1m 344/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2665 - loss: 2.2516
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2517
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2656 - loss: 2.2515
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2651 - loss: 2.2516
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2647 - loss: 2.2517
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2643 - loss: 2.2518
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2521
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2523
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2633 - loss: 2.2526
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2529
[1m 612/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2626 - loss: 2.2530
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2623 - loss: 2.2533
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2620 - loss: 2.2534
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2535
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2536
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2614 - loss: 2.2538
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2612 - loss: 2.2538
[1m 797/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2538
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2610 - loss: 2.2538
[1m 848/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2536
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2535
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2533
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2532
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2530
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2528
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2526
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2608 - loss: 2.2523
[1m1066/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2520
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2517
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2514
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2610 - loss: 2.2512
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2610 - loss: 2.2512 - val_accuracy: 0.3274 - val_loss: 2.1195
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1384
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2608 - loss: 2.1865  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2653 - loss: 2.2278
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2668 - loss: 2.2249
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2669 - loss: 2.2248
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2675 - loss: 2.2236
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2679 - loss: 2.2225
[1m 195/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.2194
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2690 - loss: 2.2175
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.2162
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2695 - loss: 2.2150
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.2138
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.2131
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2693 - loss: 2.2135
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2691 - loss: 2.2140
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2689 - loss: 2.2144
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2144
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2144
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2145
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2146
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.2146
[1m 574/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2687 - loss: 2.2148
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2687 - loss: 2.2149
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2687 - loss: 2.2151
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2686 - loss: 2.2152
[1m 685/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2686 - loss: 2.2154
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2686 - loss: 2.2154
[1m 737/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.2154
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.2153
[1m 791/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.2152
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2685 - loss: 2.2152
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2684 - loss: 2.2151
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2684 - loss: 2.2151
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2684 - loss: 2.2152
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2684 - loss: 2.2152
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2684 - loss: 2.2153
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2684 - loss: 2.2154
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.2155
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.2157
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.2158
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.2159
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.2159
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2683 - loss: 2.2160
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2683 - loss: 2.2160 - val_accuracy: 0.3458 - val_loss: 2.1277
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3292
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2287 - loss: 2.3324  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2326 - loss: 2.3058
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2374 - loss: 2.2732
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2390 - loss: 2.2560
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2404 - loss: 2.2469
[1m 157/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2426 - loss: 2.2397
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2450 - loss: 2.2332
[1m 206/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2469 - loss: 2.2280
[1m 234/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2490 - loss: 2.2224
[1m 261/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2507 - loss: 2.2187
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2525 - loss: 2.2155
[1m 319/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2541 - loss: 2.2124
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2105
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2091
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2573 - loss: 2.2077
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2581 - loss: 2.2067
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2588 - loss: 2.2059
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2593 - loss: 2.2052
[1m 513/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2598 - loss: 2.2045
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2037
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2029
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2022
[1m 618/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2016
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2012
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2621 - loss: 2.2008
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2624 - loss: 2.2004
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2627 - loss: 2.2001
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.1997
[1m 781/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.1994
[1m 810/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2636 - loss: 2.1990
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2639 - loss: 2.1986
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2642 - loss: 2.1983
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2646 - loss: 2.1979
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2648 - loss: 2.1976
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2652 - loss: 2.1972
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2655 - loss: 2.1968
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2658 - loss: 2.1964
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2661 - loss: 2.1960
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2664 - loss: 2.1957
[1m1089/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2666 - loss: 2.1954
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2669 - loss: 2.1951
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2672 - loss: 2.1947
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2673 - loss: 2.1946 - val_accuracy: 0.3470 - val_loss: 2.1164
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2705
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3156 - loss: 2.1007  
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 2.1178
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.1226
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3099 - loss: 2.1222
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3077 - loss: 2.1256
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3056 - loss: 2.1291
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3038 - loss: 2.1330
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1368
[1m 251/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 2.1391
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2987 - loss: 2.1411
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 2.1429
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2962 - loss: 2.1451
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1468
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2942 - loss: 2.1486
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2934 - loss: 2.1502
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2926 - loss: 2.1517
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1530
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1539
[1m 519/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2908 - loss: 2.1545
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2904 - loss: 2.1550
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2900 - loss: 2.1554
[1m 602/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1556
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2895 - loss: 2.1557
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2893 - loss: 2.1558
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1558
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1558
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1560
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1561
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2886 - loss: 2.1563
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2885 - loss: 2.1565
[1m 843/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1567
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1570
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2881 - loss: 2.1573
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2880 - loss: 2.1576
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2878 - loss: 2.1579
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1582
[1m1013/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2876 - loss: 2.1584
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2875 - loss: 2.1586
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2875 - loss: 2.1587
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2874 - loss: 2.1588
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1590
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2873 - loss: 2.1591
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2872 - loss: 2.1591 - val_accuracy: 0.3492 - val_loss: 2.1172
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.1594
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1619  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1415
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2902 - loss: 2.1372
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1344
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2935 - loss: 2.1298
[1m 156/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1257
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 2.1255
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2978 - loss: 2.1271
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1289
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 2.1311
[1m 293/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2965 - loss: 2.1321
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1329
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1333
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2963 - loss: 2.1335
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2966 - loss: 2.1337
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1339
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2971 - loss: 2.1342
[1m 487/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 2.1344
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 2.1348
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 2.1352
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 2.1356
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2972 - loss: 2.1359
[1m 622/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2971 - loss: 2.1363
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2971 - loss: 2.1366
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1369
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1372
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1374
[1m 761/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1376
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1377
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1379
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2968 - loss: 2.1380
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1380
[1m 905/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1379
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2969 - loss: 2.1378
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1377
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1376
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1375
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1374
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1373
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1372
[1m1112/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1370
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1369
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1368 - val_accuracy: 0.3679 - val_loss: 2.1002
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m30s[0m 26ms/step - accuracy: 0.3125 - loss: 1.7511
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0099  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0281
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0399
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3074 - loss: 2.0524
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0622
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0713
[1m 183/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0765
[1m 211/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0810
[1m 237/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 2.0841
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 2.0863
[1m 289/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.0883
[1m 316/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2982 - loss: 2.0898
[1m 342/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2980 - loss: 2.0912
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 2.0925
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 2.0937
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 2.0946
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 2.0955
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2974 - loss: 2.0961
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2975 - loss: 2.0966
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2976 - loss: 2.0973
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2976 - loss: 2.0978
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 2.0983
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2978 - loss: 2.0987
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.0990
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.0992
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 2.0995
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 2.0998
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1000
[1m 780/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1003
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1005
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1008
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1011
[1m 886/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1015
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1019
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1022
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1025
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1028
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1031
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1034
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1037
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1039
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1042
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1045 - val_accuracy: 0.3496 - val_loss: 2.1066
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.4375 - loss: 1.6065
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3397 - loss: 2.0086  
[1m  49/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3230 - loss: 2.0556
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3140 - loss: 2.0832
[1m 103/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0941
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3062 - loss: 2.0996
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3036 - loss: 2.1029
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3025 - loss: 2.1032
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 2.1031
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3018 - loss: 2.1028
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3015 - loss: 2.1023
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 2.1020
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1016
[1m 346/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3007 - loss: 2.1011
[1m 371/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 2.1008
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1005
[1m 421/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.1003
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3003 - loss: 2.1001
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1000
[1m 505/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 2.1000
[1m 531/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0998
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0994
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 2.0990
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 2.0986
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0982
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0978
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0975
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0972
[1m 744/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0970
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3001 - loss: 2.0968
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0966
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0966
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2999 - loss: 2.0965
[1m 882/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0965
[1m 909/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0964
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0964
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2999 - loss: 2.0962
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2999 - loss: 2.0962
[1m1018/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2999 - loss: 2.0961
[1m1046/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0960
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0960
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3000 - loss: 2.0960
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3001 - loss: 2.0959
[1m1154/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0959
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0959 - val_accuracy: 0.3597 - val_loss: 2.1047
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.2500 - loss: 1.8516
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2833 - loss: 2.0168  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2960 - loss: 2.0305
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.0476
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3004 - loss: 2.0571
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3011 - loss: 2.0649
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.0713
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0765
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0815
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2991 - loss: 2.0851
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.0878
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.0892
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 2.0904
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.0910
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2990 - loss: 2.0910
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 2.0908
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 2.0903
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0898
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.0895
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3012 - loss: 2.0891
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0889
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0886
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.0886
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0885
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0885
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 2.0884
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3018 - loss: 2.0883
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3019 - loss: 2.0883
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3020 - loss: 2.0882
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0880
[1m 837/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0879
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0878
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0875
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0873
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0871
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0869
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0867
[1m1024/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0864
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0862
[1m1076/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3033 - loss: 2.0859
[1m1103/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3034 - loss: 2.0857
[1m1130/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0854
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3036 - loss: 2.0852 - val_accuracy: 0.3458 - val_loss: 2.1080
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.7634
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3614 - loss: 1.9748  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3396 - loss: 2.0304
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3346 - loss: 2.0387
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0412
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3294 - loss: 2.0429
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3282 - loss: 2.0448
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0473
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3263 - loss: 2.0488
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3258 - loss: 2.0500
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3255 - loss: 2.0507
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3252 - loss: 2.0515
[1m 335/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3251 - loss: 2.0521
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3249 - loss: 2.0523
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3246 - loss: 2.0527
[1m 416/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3242 - loss: 2.0535
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3239 - loss: 2.0543
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3236 - loss: 2.0552
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0563
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3229 - loss: 2.0573
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3226 - loss: 2.0583
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0592
[1m 613/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0599
[1m 641/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0605
[1m 668/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0610
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0614
[1m 725/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3214 - loss: 2.0618
[1m 752/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0621
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3211 - loss: 2.0626
[1m 807/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0630
[1m 836/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0634
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3206 - loss: 2.0637
[1m 888/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0639
[1m 914/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3204 - loss: 2.0641
[1m 943/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0643
[1m 967/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3201 - loss: 2.0644
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0645
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3198 - loss: 2.0646
[1m1047/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3197 - loss: 2.0647
[1m1076/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0646
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0646
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3195 - loss: 2.0646
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3194 - loss: 2.0646 - val_accuracy: 0.3560 - val_loss: 2.1103
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.0157
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1217  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2932 - loss: 2.1021
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0862
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3051 - loss: 2.0740
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3083 - loss: 2.0643
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0593
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0560
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0537
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0510
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3155 - loss: 2.0485
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0463
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3175 - loss: 2.0452
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3183 - loss: 2.0438
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3188 - loss: 2.0428
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3192 - loss: 2.0421
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3196 - loss: 2.0414
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3199 - loss: 2.0407
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3202 - loss: 2.0402
[1m 529/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3205 - loss: 2.0397
[1m 555/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3208 - loss: 2.0393
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0389
[1m 610/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3213 - loss: 2.0385
[1m 640/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3215 - loss: 2.0382
[1m 669/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3217 - loss: 2.0379
[1m 696/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3219 - loss: 2.0376
[1m 724/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3221 - loss: 2.0374
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3222 - loss: 2.0372
[1m 779/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0371
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0371
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0372
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0373
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3224 - loss: 2.0374
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0375
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0375
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0375
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0376
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0376
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0376
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0376
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0376
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0377
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3223 - loss: 2.0378 - val_accuracy: 0.3554 - val_loss: 2.1145

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 641ms/step
[1m54/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 952us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:13[0m 856ms/step
[1m 49/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m102/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 998us/step
[1m158/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 962us/step
[1m206/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 984us/step
[1m260/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 973us/step
[1m315/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 966us/step
[1m370/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 959us/step
[1m426/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 954us/step
[1m477/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 959us/step
[1m534/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 951us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 56/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 916us/step
[1m107/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 950us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 33.55 [%]
Global F1 score (validation) = 32.17 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.0170321  0.02394014 0.01562569 ... 0.03251265 0.03987144 0.03125403]
 [0.00453828 0.00388151 0.00265589 ... 0.13303661 0.01031315 0.00714529]
 [0.00319506 0.00208875 0.00100362 ... 0.00741556 0.00149455 0.00156465]
 ...
 [0.16516463 0.06009054 0.12815684 ... 0.00685815 0.1598497  0.10144165]
 [0.16888218 0.07093763 0.12035618 ... 0.00790097 0.1643858  0.08724444]
 [0.15170646 0.06514312 0.1687431  ... 0.00533159 0.18202291 0.09890883]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 36.29 [%]
Global accuracy score (test) = 29.19 [%]
Global F1 score (train) = 34.18 [%]
Global F1 score (test) = 27.32 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.27      0.58      0.37       184
 CAMINAR CON MÓVIL O LIBRO       0.15      0.14      0.14       184
       CAMINAR USUAL SPEED       0.12      0.08      0.09       184
            CAMINAR ZIGZAG       0.29      0.37      0.33       184
          DE PIE BARRIENDO       0.35      0.15      0.21       184
   DE PIE DOBLANDO TOALLAS       0.31      0.24      0.28       184
    DE PIE MOVIENDO LIBROS       0.22      0.20      0.21       184
          DE PIE USANDO PC       0.22      0.30      0.25       184
        FASE REPOSO CON K5       0.37      0.68      0.48       184
INCREMENTAL CICLOERGOMETRO       0.44      0.51      0.47       184
           SENTADO LEYENDO       0.22      0.20      0.21       184
         SENTADO USANDO PC       0.15      0.02      0.04       184
      SENTADO VIENDO LA TV       0.19      0.22      0.21       184
   SUBIR Y BAJAR ESCALERAS       0.44      0.22      0.29       184
                    TROTAR       0.54      0.52      0.53       161

                  accuracy                           0.29      2737
                 macro avg       0.29      0.29      0.27      2737
              weighted avg       0.28      0.29      0.27      2737


Accuracy capturado en la ejecución 27: 29.19 [%]
F1-score capturado en la ejecución 27: 27.32 [%]

=== EJECUCIÓN 28 ===

--- TRAIN (ejecución 28) ---

--- TEST (ejecución 28) ---
2025-11-07 13:30:31.623416: 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`.
2025-11-07 13:30:31.634788: 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 00:00:1762518631.647837 2836641 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762518631.651958 2836641 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762518631.661755 2836641 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518631.661773 2836641 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518631.661775 2836641 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518631.661777 2836641 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:30:31.664896: 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 00:00:1762518633.926860 2836641 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762518637.013166 2836753 service.cc:152] XLA service 0x7a98040017c0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762518637.013220 2836753 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:30:37.083187: 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 00:00:1762518637.527307 2836753 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762518640.075408 2836753 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:44:56[0m 5s/step - accuracy: 0.0000e+00 - loss: 3.2767
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0525 - loss: 3.3881        
[1m  48/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0600 - loss: 3.3564
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0677 - loss: 3.3261
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0724 - loss: 3.3093
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0754 - loss: 3.2940
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0780 - loss: 3.2781
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0808 - loss: 3.2610
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0834 - loss: 3.2465
[1m 247/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0862 - loss: 3.2318
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0886 - loss: 3.2191
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0912 - loss: 3.2056
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0933 - loss: 3.1947
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0952 - loss: 3.1844
[1m 387/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0969 - loss: 3.1752
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0985 - loss: 3.1665
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0998 - loss: 3.1588
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1012 - loss: 3.1509
[1m 496/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1025 - loss: 3.1430
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1037 - loss: 3.1355
[1m 549/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1048 - loss: 3.1286
[1m 577/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1059 - loss: 3.1218
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1069 - loss: 3.1150
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1079 - loss: 3.1089
[1m 661/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1089 - loss: 3.1028
[1m 687/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1098 - loss: 3.0974
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1107 - loss: 3.0915
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1116 - loss: 3.0858
[1m 769/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1125 - loss: 3.0807
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1133 - loss: 3.0759
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1141 - loss: 3.0707
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1149 - loss: 3.0658
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1157 - loss: 3.0608
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1164 - loss: 3.0563
[1m 931/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1171 - loss: 3.0518
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1178 - loss: 3.0472
[1m 989/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1185 - loss: 3.0427
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1191 - loss: 3.0392
[1m1042/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1197 - loss: 3.0347
[1m1071/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1204 - loss: 3.0306
[1m1099/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1210 - loss: 3.0266
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1216 - loss: 3.0224
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1222 - loss: 3.0189
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 6ms/step - accuracy: 0.1222 - loss: 3.0187 - val_accuracy: 0.2305 - val_loss: 2.4085
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1250 - loss: 2.5926
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1933 - loss: 2.6089  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1985 - loss: 2.5868
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1959 - loss: 2.5909
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1939 - loss: 2.5987
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1939 - loss: 2.6012
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1935 - loss: 2.6040
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1930 - loss: 2.6060
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1921 - loss: 2.6079
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1912 - loss: 2.6093
[1m 273/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1908 - loss: 2.6096
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1907 - loss: 2.6092
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1906 - loss: 2.6088
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1904 - loss: 2.6084
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1904 - loss: 2.6079
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1904 - loss: 2.6076
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1903 - loss: 2.6074
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1902 - loss: 2.6074
[1m 492/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1900 - loss: 2.6074
[1m 522/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1898 - loss: 2.6073
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1896 - loss: 2.6073
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1894 - loss: 2.6072
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1893 - loss: 2.6070
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1892 - loss: 2.6066
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1892 - loss: 2.6061
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1891 - loss: 2.6056
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1890 - loss: 2.6052
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1890 - loss: 2.6047
[1m 764/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1889 - loss: 2.6043
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1888 - loss: 2.6039
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1887 - loss: 2.6036
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1886 - loss: 2.6032
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1884 - loss: 2.6028
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1883 - loss: 2.6024
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1882 - loss: 2.6018
[1m 948/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1881 - loss: 2.6014
[1m 974/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1881 - loss: 2.6009
[1m1001/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1880 - loss: 2.6004
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1880 - loss: 2.6000
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.5995
[1m1079/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.5990
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.5985
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.5981
[1m1153/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1879 - loss: 2.5976
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1879 - loss: 2.5975 - val_accuracy: 0.2819 - val_loss: 2.2562
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.1573
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2020 - loss: 2.3730  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2030 - loss: 2.4054
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2021 - loss: 2.4278
[1m 113/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2022 - loss: 2.4407
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2027 - loss: 2.4465
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2041 - loss: 2.4516
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2043 - loss: 2.4558
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.4584
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2047 - loss: 2.4605
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2050 - loss: 2.4621
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2052 - loss: 2.4641
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2053 - loss: 2.4658
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2054 - loss: 2.4674
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2055 - loss: 2.4687
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2057 - loss: 2.4697
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2059 - loss: 2.4704
[1m 463/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2061 - loss: 2.4708
[1m 488/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2062 - loss: 2.4711
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2064 - loss: 2.4716
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2064 - loss: 2.4720
[1m 570/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2064 - loss: 2.4724
[1m 597/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2064 - loss: 2.4728
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2065 - loss: 2.4731
[1m 649/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2066 - loss: 2.4732
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2066 - loss: 2.4732
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2067 - loss: 2.4733
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2068 - loss: 2.4734
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2068 - loss: 2.4734
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2069 - loss: 2.4735
[1m 817/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2070 - loss: 2.4734
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2071 - loss: 2.4733
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2072 - loss: 2.4732
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2072 - loss: 2.4731
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2073 - loss: 2.4729
[1m 955/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2074 - loss: 2.4728
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.4726
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2076 - loss: 2.4725
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2077 - loss: 2.4723
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2078 - loss: 2.4721
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2079 - loss: 2.4718
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2080 - loss: 2.4716
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2081 - loss: 2.4714
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2081 - loss: 2.4713 - val_accuracy: 0.2976 - val_loss: 2.2084
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.5828
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1798 - loss: 2.4542  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2034 - loss: 2.4225
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2092 - loss: 2.4165
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2122 - loss: 2.4125
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2139 - loss: 2.4108
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2147 - loss: 2.4112
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2150 - loss: 2.4120
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2154 - loss: 2.4118
[1m 241/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2154 - loss: 2.4118
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2154 - loss: 2.4119
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2159 - loss: 2.4115
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2163 - loss: 2.4112
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2167 - loss: 2.4109
[1m 375/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2171 - loss: 2.4104
[1m 403/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2175 - loss: 2.4099
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2178 - loss: 2.4096
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2179 - loss: 2.4093
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2182 - loss: 2.4090
[1m 506/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2184 - loss: 2.4088
[1m 535/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2186 - loss: 2.4084
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2189 - loss: 2.4079
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2191 - loss: 2.4075
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2192 - loss: 2.4072
[1m 633/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2194 - loss: 2.4066
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2196 - loss: 2.4062
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2198 - loss: 2.4056
[1m 715/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2200 - loss: 2.4051
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2201 - loss: 2.4046
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2203 - loss: 2.4041
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2205 - loss: 2.4036
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2206 - loss: 2.4030
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2208 - loss: 2.4024
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2210 - loss: 2.4019
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2211 - loss: 2.4016
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2212 - loss: 2.4012
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2213 - loss: 2.4009
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2214 - loss: 2.4006
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2215 - loss: 2.4002
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2215 - loss: 2.3997
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2216 - loss: 2.3993
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2217 - loss: 2.3989
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2218 - loss: 2.3986
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2219 - loss: 2.3981
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2219 - loss: 2.3980 - val_accuracy: 0.2978 - val_loss: 2.1766
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.1323
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2613  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2530 - loss: 2.2913
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2471 - loss: 2.3036
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2437 - loss: 2.3131
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2412 - loss: 2.3203
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2388 - loss: 2.3239
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2369 - loss: 2.3277
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2354 - loss: 2.3313
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2349 - loss: 2.3327
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3330
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2347 - loss: 2.3333
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2347 - loss: 2.3339
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2348 - loss: 2.3342
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2350 - loss: 2.3345
[1m 406/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2352 - loss: 2.3349
[1m 430/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2353 - loss: 2.3352
[1m 456/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3354
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3355
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3355
[1m 540/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3356
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3357
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3359
[1m 621/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3359
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2355 - loss: 2.3360
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3360
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3359
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3358
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3356
[1m 787/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3354
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3352
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3350
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3349
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3347
[1m 925/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3345
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3343
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3341
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3339
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3337
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3334
[1m1085/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2356 - loss: 2.3332
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2357 - loss: 2.3330
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2357 - loss: 2.3327
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2357 - loss: 2.3325 - val_accuracy: 0.3143 - val_loss: 2.1441
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.5092
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2660 - loss: 2.2653  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2620
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2576 - loss: 2.2639
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2620
[1m 136/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2611
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2532 - loss: 2.2621
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2525 - loss: 2.2637
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2516 - loss: 2.2662
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2509 - loss: 2.2681
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2503 - loss: 2.2696
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2709
[1m 325/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2724
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.2741
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2757
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2461 - loss: 2.2776
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2453 - loss: 2.2792
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2447 - loss: 2.2807
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2442 - loss: 2.2819
[1m 520/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2437 - loss: 2.2831
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2840
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2430 - loss: 2.2848
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.2852
[1m 630/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2856
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2859
[1m 682/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2862
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2863
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2865
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2868
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2426 - loss: 2.2870
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2426 - loss: 2.2873
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2875
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2427 - loss: 2.2875
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2428 - loss: 2.2875
[1m 939/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2429 - loss: 2.2874
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2430 - loss: 2.2873
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2431 - loss: 2.2871
[1m1023/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2869
[1m1051/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2434 - loss: 2.2867
[1m1081/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2435 - loss: 2.2865
[1m1105/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2436 - loss: 2.2863
[1m1133/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2438 - loss: 2.2861
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2439 - loss: 2.2860 - val_accuracy: 0.3147 - val_loss: 2.1520
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.0625 - loss: 2.4021
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2098 - loss: 2.3389  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2295 - loss: 2.2991
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2369 - loss: 2.2823
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2407 - loss: 2.2739
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2423 - loss: 2.2708
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2429 - loss: 2.2706
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2431 - loss: 2.2704
[1m 224/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2432 - loss: 2.2694
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2433 - loss: 2.2682
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2436 - loss: 2.2672
[1m 303/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2441 - loss: 2.2659
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2447 - loss: 2.2644
[1m 360/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2450 - loss: 2.2634
[1m 390/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2453 - loss: 2.2627
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2454 - loss: 2.2624
[1m 437/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2456 - loss: 2.2622
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2458 - loss: 2.2620
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2460 - loss: 2.2619
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2462 - loss: 2.2618
[1m 548/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2617
[1m 576/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2617
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2618
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2463 - loss: 2.2618
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2465 - loss: 2.2617
[1m 690/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2467 - loss: 2.2615
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2468 - loss: 2.2613
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2470 - loss: 2.2612
[1m 772/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2472 - loss: 2.2610
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2473 - loss: 2.2608
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2475 - loss: 2.2606
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2477 - loss: 2.2604
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2478 - loss: 2.2602
[1m 902/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2480 - loss: 2.2600
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2481 - loss: 2.2598
[1m 958/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2483 - loss: 2.2597
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2595
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2593
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2591
[1m1070/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2490 - loss: 2.2589
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2587
[1m1124/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2493 - loss: 2.2585
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2494 - loss: 2.2583
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2494 - loss: 2.2582 - val_accuracy: 0.3242 - val_loss: 2.1515
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.1250 - loss: 2.4845
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2749 - loss: 2.1928  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2689 - loss: 2.1994
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2676 - loss: 2.2047
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2649 - loss: 2.2094
[1m 137/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2623 - loss: 2.2134
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2148
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2610 - loss: 2.2159
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2607 - loss: 2.2164
[1m 246/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2605 - loss: 2.2172
[1m 274/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2175
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2177
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2176
[1m 354/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2600 - loss: 2.2173
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2603 - loss: 2.2168
[1m 410/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2606 - loss: 2.2162
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2609 - loss: 2.2160
[1m 464/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2611 - loss: 2.2159
[1m 491/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2613 - loss: 2.2158
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2615 - loss: 2.2158
[1m 546/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2158
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2616 - loss: 2.2158
[1m 598/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2618 - loss: 2.2157
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2619 - loss: 2.2154
[1m 650/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2621 - loss: 2.2151
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2623 - loss: 2.2149
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2625 - loss: 2.2146
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2626 - loss: 2.2144
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2628 - loss: 2.2142
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2141
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2629 - loss: 2.2141
[1m 838/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2630 - loss: 2.2139
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2631 - loss: 2.2138
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2632 - loss: 2.2137
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2633 - loss: 2.2135
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2634 - loss: 2.2133
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2635 - loss: 2.2131
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2636 - loss: 2.2129
[1m1037/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2637 - loss: 2.2126
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2638 - loss: 2.2125
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2639 - loss: 2.2122
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2121
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2119
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2640 - loss: 2.2119 - val_accuracy: 0.3407 - val_loss: 2.1075
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.1554
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1685  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2974 - loss: 2.1781
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2912 - loss: 2.1939
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2899 - loss: 2.1984
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1978
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1968
[1m 190/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2868 - loss: 2.1964
[1m 217/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1963
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1962
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1959
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2844 - loss: 2.1957
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1954
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1945
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1931
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1919
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1908
[1m 468/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1901
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2840 - loss: 2.1896
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2839 - loss: 2.1892
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2838 - loss: 2.1888
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1885
[1m 606/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2836 - loss: 2.1882
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1878
[1m 659/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2835 - loss: 2.1873
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2834 - loss: 2.1869
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1866
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1862
[1m 768/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2832 - loss: 2.1859
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1856
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1852
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1849
[1m 873/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1847
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1845
[1m 929/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1842
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2830 - loss: 2.1840
[1m 984/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1838
[1m1011/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1836
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1835
[1m1062/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1833
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1832
[1m1113/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2829 - loss: 2.1831
[1m1141/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1829
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1828 - val_accuracy: 0.3373 - val_loss: 2.1101
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.4208
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1711  
[1m  53/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1441
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2903 - loss: 2.1391
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2905 - loss: 2.1417
[1m 139/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2902 - loss: 2.1443
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2899 - loss: 2.1454
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2899 - loss: 2.1463
[1m 223/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1474
[1m 252/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2882 - loss: 2.1492
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2872 - loss: 2.1503
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1511
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1519
[1m 364/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2848 - loss: 2.1527
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2842 - loss: 2.1535
[1m 419/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2837 - loss: 2.1544
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2833 - loss: 2.1552
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2831 - loss: 2.1558
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2828 - loss: 2.1564
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2825 - loss: 2.1569
[1m 558/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2824 - loss: 2.1571
[1m 587/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2823 - loss: 2.1573
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2822 - loss: 2.1574
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2821 - loss: 2.1575
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2820 - loss: 2.1574
[1m 701/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1574
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1574
[1m 756/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1572
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1571
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1570
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1569
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1568
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1566
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1565
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1564
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2816 - loss: 2.1563
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1561
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1560
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2817 - loss: 2.1559
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1558
[1m1117/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2818 - loss: 2.1556
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1554
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2819 - loss: 2.1554 - val_accuracy: 0.3341 - val_loss: 2.1044
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.1875 - loss: 2.3029
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2210 - loss: 2.2621  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2306 - loss: 2.2394
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2413 - loss: 2.2198
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2077
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2515 - loss: 2.2023
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.1977
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2565 - loss: 2.1929
[1m 220/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2590 - loss: 2.1891
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2613 - loss: 2.1855
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2629 - loss: 2.1825
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2643 - loss: 2.1800
[1m 329/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2654 - loss: 2.1780
[1m 357/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2667 - loss: 2.1757
[1m 384/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2677 - loss: 2.1738
[1m 413/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.1720
[1m 440/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2694 - loss: 2.1704
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2700 - loss: 2.1692
[1m 494/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2707 - loss: 2.1680
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.1667
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2720 - loss: 2.1657
[1m 579/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1649
[1m 608/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2730 - loss: 2.1642
[1m 639/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2735 - loss: 2.1635
[1m 665/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2739 - loss: 2.1630
[1m 693/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2743 - loss: 2.1625
[1m 723/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2746 - loss: 2.1619
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2749 - loss: 2.1615
[1m 778/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2752 - loss: 2.1611
[1m 805/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2755 - loss: 2.1607
[1m 831/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2758 - loss: 2.1603
[1m 859/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2761 - loss: 2.1599
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2764 - loss: 2.1595
[1m 913/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2767 - loss: 2.1591
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2769 - loss: 2.1587
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1583
[1m 998/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2774 - loss: 2.1580
[1m1026/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2777 - loss: 2.1576
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2779 - loss: 2.1572
[1m1083/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2781 - loss: 2.1568
[1m1109/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2784 - loss: 2.1564
[1m1134/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2786 - loss: 2.1560
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1557 - val_accuracy: 0.3441 - val_loss: 2.0999
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3750 - loss: 2.1020
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3416 - loss: 2.0262  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3253 - loss: 2.0485
[1m  80/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3159 - loss: 2.0648
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3127 - loss: 2.0721
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0784
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0833
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3078 - loss: 2.0859
[1m 214/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0878
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3064 - loss: 2.0895
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3059 - loss: 2.0910
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3055 - loss: 2.0921
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3052 - loss: 2.0931
[1m 350/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0940
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3042 - loss: 2.0950
[1m 402/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3035 - loss: 2.0962
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0973
[1m 454/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0983
[1m 481/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3019 - loss: 2.0992
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0999
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3009 - loss: 2.1006
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.1013
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1019
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 2.1023
[1m 647/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2996 - loss: 2.1027
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2993 - loss: 2.1031
[1m 703/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2991 - loss: 2.1033
[1m 732/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2988 - loss: 2.1037
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2986 - loss: 2.1041
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1044
[1m 815/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1046
[1m 844/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2983 - loss: 2.1047
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1049
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2982 - loss: 2.1050
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1051
[1m 952/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1052
[1m 977/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1054
[1m1004/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2980 - loss: 2.1055
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1057
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1058
[1m1088/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1060
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1060
[1m1143/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1061
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2979 - loss: 2.1061 - val_accuracy: 0.3311 - val_loss: 2.0697
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.5822
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2866 - loss: 2.1918  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2925 - loss: 2.1662
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1440
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 2.1273
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 2.1195
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2992 - loss: 2.1166
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2995 - loss: 2.1149
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.1134
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3010 - loss: 2.1123
[1m 268/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1120
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 2.1119
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 2.1118
[1m 351/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1116
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3013 - loss: 2.1113
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3015 - loss: 2.1110
[1m 433/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3016 - loss: 2.1106
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3018 - loss: 2.1101
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3019 - loss: 2.1095
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3020 - loss: 2.1088
[1m 543/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3021 - loss: 2.1082
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3022 - loss: 2.1076
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3024 - loss: 2.1069
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.1062
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.1054
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.1048
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3032 - loss: 2.1042
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3035 - loss: 2.1037
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3037 - loss: 2.1031
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3039 - loss: 2.1027
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3041 - loss: 2.1023
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3042 - loss: 2.1020
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3043 - loss: 2.1017
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3045 - loss: 2.1014
[1m 932/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3046 - loss: 2.1012
[1m 957/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 2.1010
[1m 983/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3047 - loss: 2.1008
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 2.1006
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 2.1004
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 2.1003
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 2.1001
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 2.1000
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0998
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0998 - val_accuracy: 0.3407 - val_loss: 2.0997
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.4375 - loss: 1.7268
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3401 - loss: 2.0313  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3310 - loss: 2.0597
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3290 - loss: 2.0637
[1m 104/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0675
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3216 - loss: 2.0735
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3185 - loss: 2.0765
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3166 - loss: 2.0771
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0772
[1m 240/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0769
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0754
[1m 296/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0745
[1m 322/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3135 - loss: 2.0747
[1m 349/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0752
[1m 379/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0758
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0765
[1m 432/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0771
[1m 461/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0774
[1m 489/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0777
[1m 516/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3108 - loss: 2.0781
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0783
[1m 568/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0786
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0789
[1m 626/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3100 - loss: 2.0791
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3099 - loss: 2.0791
[1m 680/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3097 - loss: 2.0792
[1m 707/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3096 - loss: 2.0795
[1m 731/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0797
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0799
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0800
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3094 - loss: 2.0800
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0801
[1m 871/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3093 - loss: 2.0802
[1m 899/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0803
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3091 - loss: 2.0804
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3090 - loss: 2.0804
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3089 - loss: 2.0804
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3088 - loss: 2.0805
[1m1040/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3087 - loss: 2.0805
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3086 - loss: 2.0806
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3086 - loss: 2.0806
[1m1121/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0806
[1m1149/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0806
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3085 - loss: 2.0806 - val_accuracy: 0.3339 - val_loss: 2.0795
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 23ms/step - accuracy: 0.3750 - loss: 1.9464
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2798 - loss: 2.0389  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2946 - loss: 2.0476
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2998 - loss: 2.0499
[1m 111/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3047 - loss: 2.0479
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3070 - loss: 2.0486
[1m 167/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3092 - loss: 2.0499
[1m 194/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3098 - loss: 2.0522
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0537
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3106 - loss: 2.0544
[1m 275/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3104 - loss: 2.0556
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0567
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0570
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3101 - loss: 2.0570
[1m 382/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0569
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0569
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3102 - loss: 2.0571
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3103 - loss: 2.0573
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3105 - loss: 2.0574
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0574
[1m 544/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0574
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0576
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0580
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0584
[1m 655/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0588
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3110 - loss: 2.0591
[1m 710/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3111 - loss: 2.0593
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3112 - loss: 2.0594
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0594
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3114 - loss: 2.0594
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3115 - loss: 2.0592
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0591
[1m 876/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0591
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0590
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0591
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0591
[1m 988/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0591
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0591
[1m1044/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0592
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0592
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0593
[1m1129/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0593
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3116 - loss: 2.0594 - val_accuracy: 0.3329 - val_loss: 2.0865
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m40s[0m 35ms/step - accuracy: 0.4375 - loss: 1.6306
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.4016 - loss: 1.9163  
[1m  55/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3782 - loss: 1.9411
[1m  83/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3672 - loss: 1.9654
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3602 - loss: 1.9795
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3569 - loss: 1.9850
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3549 - loss: 1.9890
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3534 - loss: 1.9923
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3520 - loss: 1.9953
[1m 248/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3503 - loss: 1.9985
[1m 278/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3490 - loss: 2.0007
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3480 - loss: 2.0026
[1m 332/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3469 - loss: 2.0044
[1m 359/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3458 - loss: 2.0062
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3446 - loss: 2.0082
[1m 418/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3435 - loss: 2.0098
[1m 447/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3427 - loss: 2.0109
[1m 473/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3420 - loss: 2.0122
[1m 500/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3414 - loss: 2.0131
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3409 - loss: 2.0138
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3405 - loss: 2.0144
[1m 582/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3402 - loss: 2.0150
[1m 611/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3399 - loss: 2.0157
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3396 - loss: 2.0163
[1m 658/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3393 - loss: 2.0169
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3389 - loss: 2.0178
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3385 - loss: 2.0186
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3382 - loss: 2.0193
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3379 - loss: 2.0199
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3376 - loss: 2.0204
[1m 820/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3373 - loss: 2.0209
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3369 - loss: 2.0214
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3366 - loss: 2.0219
[1m 906/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3363 - loss: 2.0224
[1m 934/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3360 - loss: 2.0229
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3358 - loss: 2.0233
[1m 985/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3356 - loss: 2.0238
[1m1012/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3353 - loss: 2.0243
[1m1039/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3351 - loss: 2.0248
[1m1065/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3348 - loss: 2.0252
[1m1094/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3345 - loss: 2.0258
[1m1122/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3343 - loss: 2.0262
[1m1151/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3340 - loss: 2.0267
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3340 - loss: 2.0267 - val_accuracy: 0.3357 - val_loss: 2.1080
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.2500 - loss: 2.0016
[1m  25/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3164 - loss: 1.9695  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3290 - loss: 1.9817
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3315 - loss: 1.9939
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3330 - loss: 2.0003
[1m 138/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3340 - loss: 2.0050
[1m 166/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3349 - loss: 2.0061
[1m 196/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3353 - loss: 2.0074
[1m 222/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 2.0083
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3356 - loss: 2.0097
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3355 - loss: 2.0108
[1m 307/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3353 - loss: 2.0116
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3349 - loss: 2.0125
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3344 - loss: 2.0134
[1m 391/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3338 - loss: 2.0145
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3333 - loss: 2.0153
[1m 448/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 2.0158
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3326 - loss: 2.0163
[1m 502/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3324 - loss: 2.0167
[1m 530/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3321 - loss: 2.0173
[1m 557/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3319 - loss: 2.0179
[1m 584/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3317 - loss: 2.0185
[1m 614/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3314 - loss: 2.0191
[1m 642/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3312 - loss: 2.0195
[1m 671/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3310 - loss: 2.0199
[1m 698/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3308 - loss: 2.0203
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3307 - loss: 2.0206
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0208
[1m 785/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3304 - loss: 2.0211
[1m 812/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0213
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3302 - loss: 2.0215
[1m 869/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3301 - loss: 2.0216
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3300 - loss: 2.0217
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3299 - loss: 2.0219
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3297 - loss: 2.0220
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3296 - loss: 2.0221
[1m1007/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3295 - loss: 2.0223
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3294 - loss: 2.0224
[1m1063/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3294 - loss: 2.0224
[1m1092/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3294 - loss: 2.0225
[1m1120/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3293 - loss: 2.0226
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3293 - loss: 2.0226
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3293 - loss: 2.0226 - val_accuracy: 0.3339 - val_loss: 2.1131

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 641ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 986us/step 
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 8ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:07[0m 845ms/step
[1m 51/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step    
[1m101/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step
[1m158/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 964us/step
[1m207/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 978us/step
[1m255/578[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m0s[0m 992us/step
[1m311/578[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 975us/step
[1m369/578[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 957us/step
[1m421/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 958us/step
[1m477/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 952us/step
[1m530/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 953us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 15ms/step
[1m55/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 936us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 52/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 995us/step
[1m111/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 923us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 35.54 [%]
Global F1 score (validation) = 34.98 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.02429604 0.0154941  0.01269719 ... 0.03187022 0.03220557 0.01683672]
 [0.00489324 0.00431141 0.00386434 ... 0.11902425 0.01168302 0.00629499]
 [0.00145616 0.00036815 0.00065503 ... 0.00123229 0.00150277 0.00108798]
 ...
 [0.11331379 0.05283178 0.19147952 ... 0.00667865 0.18442595 0.13766381]
 [0.11310061 0.05685176 0.21844764 ... 0.01408751 0.10988918 0.14260446]
 [0.07801781 0.0520916  0.26548314 ... 0.00225524 0.21297726 0.09714093]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 38.74 [%]
Global accuracy score (test) = 28.32 [%]
Global F1 score (train) = 38.75 [%]
Global F1 score (test) = 28.04 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.31      0.47      0.37       184
 CAMINAR CON MÓVIL O LIBRO       0.21      0.15      0.17       184
       CAMINAR USUAL SPEED       0.30      0.31      0.31       184
            CAMINAR ZIGZAG       0.29      0.22      0.25       184
          DE PIE BARRIENDO       0.40      0.20      0.27       184
   DE PIE DOBLANDO TOALLAS       0.29      0.49      0.36       184
    DE PIE MOVIENDO LIBROS       0.20      0.14      0.17       184
          DE PIE USANDO PC       0.10      0.14      0.11       184
        FASE REPOSO CON K5       0.50      0.46      0.48       184
INCREMENTAL CICLOERGOMETRO       0.57      0.38      0.45       184
           SENTADO LEYENDO       0.30      0.26      0.27       184
         SENTADO USANDO PC       0.22      0.29      0.25       184
      SENTADO VIENDO LA TV       0.14      0.20      0.16       184
   SUBIR Y BAJAR ESCALERAS       0.17      0.07      0.09       184
                    TROTAR       0.45      0.52      0.48       161

                  accuracy                           0.28      2737
                 macro avg       0.30      0.29      0.28      2737
              weighted avg       0.29      0.28      0.28      2737


Accuracy capturado en la ejecución 28: 28.32 [%]
F1-score capturado en la ejecución 28: 28.04 [%]

=== EJECUCIÓN 29 ===

--- TRAIN (ejecución 29) ---

--- TEST (ejecución 29) ---
2025-11-07 13:31:40.323038: 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`.
2025-11-07 13:31:40.334383: 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 00:00:1762518700.347482 2839581 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1762518700.351585 2839581 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1762518700.361493 2839581 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518700.361511 2839581 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518700.361520 2839581 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1762518700.361521 2839581 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
2025-11-07 13:31:40.364699: 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 00:00:1762518702.602906 2839581 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13760 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 1/27
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1762518705.690989 2839714 service.cc:152] XLA service 0x7e53d4002d50 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
I0000 00:00:1762518705.691042 2839714 service.cc:160]   StreamExecutor device (0): NVIDIA GeForce RTX 4060 Ti, Compute Capability 8.9
2025-11-07 13:31:45.760621: 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 00:00:1762518706.184860 2839714 cuda_dnn.cc:529] Loaded cuDNN version 91002
I0000 00:00:1762518708.697006 2839714 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1:43:58[0m 5s/step - accuracy: 0.0625 - loss: 3.6811
[1m  23/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0819 - loss: 3.3394    
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0808 - loss: 3.3095
[1m  75/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0833 - loss: 3.2935
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0850 - loss: 3.2789
[1m 130/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.0857 - loss: 3.2709
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0869 - loss: 3.2632
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0881 - loss: 3.2539
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0891 - loss: 3.2464
[1m 243/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0899 - loss: 3.2392
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0907 - loss: 3.2319
[1m 302/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0915 - loss: 3.2244
[1m 330/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0920 - loss: 3.2174
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0924 - loss: 3.2107
[1m 385/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0928 - loss: 3.2047
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0931 - loss: 3.1990
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0936 - loss: 3.1934
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0942 - loss: 3.1867
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0947 - loss: 3.1808
[1m 528/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0953 - loss: 3.1745
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0958 - loss: 3.1687
[1m 586/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.0964 - loss: 3.1627
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0971 - loss: 3.1566
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0977 - loss: 3.1514
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0983 - loss: 3.1460
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0990 - loss: 3.1408
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.0997 - loss: 3.1356
[1m 758/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1004 - loss: 3.1300
[1m 788/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1012 - loss: 3.1245
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1018 - loss: 3.1200
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1025 - loss: 3.1156
[1m 865/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1031 - loss: 3.1113
[1m 894/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1038 - loss: 3.1065
[1m 920/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1045 - loss: 3.1022
[1m 949/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1052 - loss: 3.0976
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1058 - loss: 3.0933
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1065 - loss: 3.0886
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1071 - loss: 3.0842
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1076 - loss: 3.0806
[1m1090/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1083 - loss: 3.0763
[1m1119/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1089 - loss: 3.0722
[1m1147/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1094 - loss: 3.0684
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step - accuracy: 0.1096 - loss: 3.0673
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m12s[0m 5ms/step - accuracy: 0.1096 - loss: 3.0672 - val_accuracy: 0.2156 - val_loss: 2.3913
Epoch 2/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.1875 - loss: 2.4479
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1584 - loss: 2.7790  
[1m  50/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1642 - loss: 2.7484
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1660 - loss: 2.7283
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1675 - loss: 2.7167
[1m 128/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1694 - loss: 2.7083
[1m 153/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1708 - loss: 2.7063
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1713 - loss: 2.7050
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1715 - loss: 2.7046
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1721 - loss: 2.7033
[1m 267/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1727 - loss: 2.7015
[1m 295/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1729 - loss: 2.7003
[1m 324/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1731 - loss: 2.6988
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1733 - loss: 2.6973
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1735 - loss: 2.6960
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.6950
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.6941
[1m 459/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.6932
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1734 - loss: 2.6921
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1735 - loss: 2.6910
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1737 - loss: 2.6899
[1m 560/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1738 - loss: 2.6889
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1740 - loss: 2.6874
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1742 - loss: 2.6861
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1743 - loss: 2.6850
[1m 674/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1745 - loss: 2.6839
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1746 - loss: 2.6828
[1m 727/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1747 - loss: 2.6819
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1748 - loss: 2.6808
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1749 - loss: 2.6797
[1m 808/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1750 - loss: 2.6787
[1m 835/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1751 - loss: 2.6776
[1m 864/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1753 - loss: 2.6764
[1m 893/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1754 - loss: 2.6753
[1m 922/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1755 - loss: 2.6742
[1m 950/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1756 - loss: 2.6732
[1m 979/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1757 - loss: 2.6722
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1758 - loss: 2.6713
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1759 - loss: 2.6703
[1m1058/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1760 - loss: 2.6695
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1761 - loss: 2.6685
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1762 - loss: 2.6676
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1763 - loss: 2.6666
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1763 - loss: 2.6661 - val_accuracy: 0.2571 - val_loss: 2.3086
Epoch 3/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1250 - loss: 2.5191
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2099 - loss: 2.4831  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1999 - loss: 2.4950
[1m  81/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1992 - loss: 2.4940
[1m 108/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1990 - loss: 2.4970
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1987 - loss: 2.5021
[1m 162/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1988 - loss: 2.5050
[1m 189/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1986 - loss: 2.5056
[1m 216/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1985 - loss: 2.5048
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1982 - loss: 2.5053
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1978 - loss: 2.5062
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1976 - loss: 2.5069
[1m 327/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1975 - loss: 2.5078
[1m 353/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1974 - loss: 2.5086
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1973 - loss: 2.5096
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1972 - loss: 2.5102
[1m 434/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1970 - loss: 2.5110
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1968 - loss: 2.5119
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1966 - loss: 2.5127
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1964 - loss: 2.5131
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1964 - loss: 2.5136
[1m 569/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1963 - loss: 2.5140
[1m 596/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1963 - loss: 2.5143
[1m 624/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1963 - loss: 2.5145
[1m 653/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1963 - loss: 2.5146
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1963 - loss: 2.5146
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1963 - loss: 2.5144
[1m 738/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1964 - loss: 2.5141
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1965 - loss: 2.5138
[1m 792/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1966 - loss: 2.5134
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1967 - loss: 2.5129
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1969 - loss: 2.5124
[1m 877/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1970 - loss: 2.5118
[1m 904/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1972 - loss: 2.5112
[1m 933/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1973 - loss: 2.5106
[1m 959/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1975 - loss: 2.5100
[1m 987/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1977 - loss: 2.5094
[1m1014/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.1978 - loss: 2.5089
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1979 - loss: 2.5083
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1981 - loss: 2.5078
[1m1093/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.1982 - loss: 2.5073
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1983 - loss: 2.5069
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.1984 - loss: 2.5063
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.1985 - loss: 2.5061 - val_accuracy: 0.2611 - val_loss: 2.2573
Epoch 4/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 20ms/step - accuracy: 0.3125 - loss: 2.4032
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.1828 - loss: 2.5143  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1831 - loss: 2.5119
[1m  87/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1864 - loss: 2.5018
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1907 - loss: 2.4897
[1m 148/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1943 - loss: 2.4787
[1m 177/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1960 - loss: 2.4733
[1m 204/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1973 - loss: 2.4694
[1m 234/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1984 - loss: 2.4657
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1990 - loss: 2.4637
[1m 291/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.1996 - loss: 2.4624
[1m 320/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2003 - loss: 2.4610
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2008 - loss: 2.4599
[1m 378/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2015 - loss: 2.4586
[1m 408/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2020 - loss: 2.4571
[1m 435/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2026 - loss: 2.4554
[1m 462/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2031 - loss: 2.4541
[1m 490/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2036 - loss: 2.4528
[1m 518/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2041 - loss: 2.4515
[1m 545/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2045 - loss: 2.4504
[1m 573/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2050 - loss: 2.4492
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2054 - loss: 2.4481
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2058 - loss: 2.4471
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2062 - loss: 2.4463
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2066 - loss: 2.4455
[1m 717/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2069 - loss: 2.4446
[1m 745/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2072 - loss: 2.4437
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2075 - loss: 2.4429
[1m 804/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2078 - loss: 2.4421
[1m 832/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2080 - loss: 2.4414
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2082 - loss: 2.4408
[1m 890/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2084 - loss: 2.4402
[1m 915/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2086 - loss: 2.4396
[1m 942/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2088 - loss: 2.4391
[1m 969/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2089 - loss: 2.4386
[1m 996/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2091 - loss: 2.4381
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2092 - loss: 2.4377
[1m1048/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2093 - loss: 2.4373
[1m1077/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2095 - loss: 2.4368
[1m1104/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2096 - loss: 2.4363
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2098 - loss: 2.4357
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2099 - loss: 2.4353 - val_accuracy: 0.2783 - val_loss: 2.2254
Epoch 5/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.2500 - loss: 2.4867
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2290 - loss: 2.3851  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2268 - loss: 2.3758
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2245 - loss: 2.3768
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2233 - loss: 2.3771
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2219 - loss: 2.3782
[1m 173/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2213 - loss: 2.3777
[1m 202/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2212 - loss: 2.3764
[1m 227/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2211 - loss: 2.3760
[1m 256/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2206 - loss: 2.3760
[1m 285/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2202 - loss: 2.3760
[1m 312/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.3754
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2200 - loss: 2.3748
[1m 369/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2200 - loss: 2.3743
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2200 - loss: 2.3738
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.3730
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2201 - loss: 2.3723
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2202 - loss: 2.3718
[1m 515/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2202 - loss: 2.3713
[1m 541/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2202 - loss: 2.3709
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2202 - loss: 2.3705
[1m 600/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2202 - loss: 2.3703
[1m 629/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2202 - loss: 2.3701
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2203 - loss: 2.3699
[1m 679/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2204 - loss: 2.3697
[1m 709/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2204 - loss: 2.3694
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2205 - loss: 2.3692
[1m 763/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2206 - loss: 2.3689
[1m 790/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2207 - loss: 2.3685
[1m 816/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2208 - loss: 2.3682
[1m 842/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2209 - loss: 2.3679
[1m 867/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2211 - loss: 2.3675
[1m 895/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2212 - loss: 2.3672
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2213 - loss: 2.3669
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2215 - loss: 2.3666
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2216 - loss: 2.3663
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2218 - loss: 2.3658
[1m1036/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2219 - loss: 2.3655
[1m1061/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2220 - loss: 2.3652
[1m1086/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2221 - loss: 2.3649
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2223 - loss: 2.3646
[1m1142/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2224 - loss: 2.3642
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2225 - loss: 2.3641 - val_accuracy: 0.2893 - val_loss: 2.1771
Epoch 6/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m28s[0m 25ms/step - accuracy: 0.2500 - loss: 1.9297
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2726  
[1m  59/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2806
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2479 - loss: 2.2897
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2929
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2482 - loss: 2.2965
[1m 165/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2481 - loss: 2.2996
[1m 193/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2476 - loss: 2.3026
[1m 221/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2477 - loss: 2.3039
[1m 250/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2481 - loss: 2.3036
[1m 277/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2486 - loss: 2.3027
[1m 304/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2491 - loss: 2.3016
[1m 331/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2495 - loss: 2.3004
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2994
[1m 383/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2986
[1m 409/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2500 - loss: 2.2980
[1m 438/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2499 - loss: 2.2977
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2498 - loss: 2.2976
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2496 - loss: 2.2978
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2494 - loss: 2.2980
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2493 - loss: 2.2979
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2978
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2977
[1m 631/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2975
[1m 656/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2974
[1m 684/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2973
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2974
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2974
[1m 767/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2975
[1m 795/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2492 - loss: 2.2977
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2978
[1m 847/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2979
[1m 874/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2491 - loss: 2.2979
[1m 898/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2490 - loss: 2.2979
[1m 923/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2490 - loss: 2.2979
[1m 951/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2489 - loss: 2.2979
[1m 978/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2489 - loss: 2.2979
[1m1006/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2489 - loss: 2.2978
[1m1032/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2978
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2488 - loss: 2.2978
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2487 - loss: 2.2977
[1m1114/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2486 - loss: 2.2977
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2977
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2485 - loss: 2.2978 - val_accuracy: 0.2974 - val_loss: 2.1580
Epoch 7/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.1875 - loss: 2.4948
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2318 - loss: 2.2651  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2475 - loss: 2.2489
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2503 - loss: 2.2512
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2516 - loss: 2.2523
[1m 143/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2535 - loss: 2.2517
[1m 170/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2545 - loss: 2.2529
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2550
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2549 - loss: 2.2573
[1m 257/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2590
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2546 - loss: 2.2607
[1m 313/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2616
[1m 340/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2542 - loss: 2.2622
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2540 - loss: 2.2629
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2537 - loss: 2.2635
[1m 420/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2534 - loss: 2.2642
[1m 449/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2531 - loss: 2.2649
[1m 477/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2528 - loss: 2.2656
[1m 508/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2526 - loss: 2.2662
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2524 - loss: 2.2666
[1m 559/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2522 - loss: 2.2669
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2522 - loss: 2.2673
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2521 - loss: 2.2676
[1m 645/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2520 - loss: 2.2677
[1m 670/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2519 - loss: 2.2678
[1m 697/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2518 - loss: 2.2678
[1m 721/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2518 - loss: 2.2679
[1m 750/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2517 - loss: 2.2679
[1m 774/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2516 - loss: 2.2680
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2516 - loss: 2.2681
[1m 828/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2515 - loss: 2.2682
[1m 857/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2514 - loss: 2.2684
[1m 885/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2684
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2513 - loss: 2.2684
[1m 936/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2685
[1m 963/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2685
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2685
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2685
[1m1049/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2684
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2683
[1m1108/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2681
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2680
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2512 - loss: 2.2680 - val_accuracy: 0.3113 - val_loss: 2.1215
Epoch 8/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.0625 - loss: 2.8248
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2206 - loss: 2.3556  
[1m  57/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2319 - loss: 2.3153
[1m  88/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2381 - loss: 2.2957
[1m 116/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2435 - loss: 2.2823
[1m 146/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2474 - loss: 2.2752
[1m 172/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2502 - loss: 2.2690
[1m 200/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2520 - loss: 2.2643
[1m 225/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2531 - loss: 2.2613
[1m 253/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2539 - loss: 2.2589
[1m 279/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2544 - loss: 2.2576
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2548 - loss: 2.2563
[1m 339/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2551 - loss: 2.2556
[1m 367/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2552 - loss: 2.2551
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2545
[1m 424/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2538
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2535
[1m 478/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2531
[1m 504/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2553 - loss: 2.2530
[1m 533/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2529
[1m 562/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2528
[1m 588/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2554 - loss: 2.2526
[1m 615/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2555 - loss: 2.2522
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2557 - loss: 2.2518
[1m 667/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2558 - loss: 2.2515
[1m 694/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2559 - loss: 2.2511
[1m 720/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2560 - loss: 2.2507
[1m 749/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2502
[1m 775/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2499
[1m 802/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2495
[1m 827/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2492
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2489
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2487
[1m 911/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2484
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2482
[1m 965/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2480
[1m 994/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2561 - loss: 2.2477
[1m1020/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2475
[1m1045/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2562 - loss: 2.2472
[1m1073/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2469
[1m1100/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2563 - loss: 2.2465
[1m1127/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2462
[1m1152/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2564 - loss: 2.2459
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2565 - loss: 2.2458 - val_accuracy: 0.3095 - val_loss: 2.1270
Epoch 9/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.2748
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2407 - loss: 2.2991  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2528 - loss: 2.2604
[1m  78/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2408
[1m 102/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2604 - loss: 2.2293
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2624 - loss: 2.2210
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2651 - loss: 2.2148
[1m 186/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2668 - loss: 2.2115
[1m 213/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2678 - loss: 2.2093
[1m 242/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2681 - loss: 2.2084
[1m 271/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2686 - loss: 2.2073
[1m 301/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2692 - loss: 2.2063
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2698 - loss: 2.2051
[1m 358/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2701 - loss: 2.2042
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2703 - loss: 2.2038
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2704 - loss: 2.2036
[1m 444/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2705 - loss: 2.2034
[1m 469/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2706 - loss: 2.2030
[1m 498/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2707 - loss: 2.2027
[1m 524/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2709 - loss: 2.2021
[1m 550/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2711 - loss: 2.2016
[1m 578/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2714 - loss: 2.2011
[1m 604/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2715 - loss: 2.2006
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2718 - loss: 2.2001
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2720 - loss: 2.1996
[1m 683/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2721 - loss: 2.1992
[1m 712/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2723 - loss: 2.1988
[1m 739/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1984
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1982
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1980
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2726 - loss: 2.1978
[1m 852/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1978
[1m 881/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1977
[1m 910/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1977
[1m 938/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1976
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1976
[1m 995/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1976
[1m1022/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1975
[1m1052/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1976
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1976
[1m1106/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1977
[1m1137/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1978
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2727 - loss: 2.1979 - val_accuracy: 0.3294 - val_loss: 2.1109
Epoch 10/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3750 - loss: 2.1551
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2578 - loss: 2.2294  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2675 - loss: 2.2009
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2696 - loss: 2.1917
[1m 115/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2688 - loss: 2.1890
[1m 144/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2689 - loss: 2.1868
[1m 174/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2689 - loss: 2.1855
[1m 204/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2697 - loss: 2.1834
[1m 230/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2708 - loss: 2.1816
[1m 257/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2716 - loss: 2.1807
[1m 285/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2725 - loss: 2.1796
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2734 - loss: 2.1787
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2741 - loss: 2.1780
[1m 372/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2747 - loss: 2.1772
[1m 400/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2751 - loss: 2.1766
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2755 - loss: 2.1762
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2759 - loss: 2.1757
[1m 483/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2762 - loss: 2.1752
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2766 - loss: 2.1747
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2770 - loss: 2.1744
[1m 565/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2772 - loss: 2.1741
[1m 593/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2775 - loss: 2.1737
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2778 - loss: 2.1731
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2781 - loss: 2.1727
[1m 675/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2783 - loss: 2.1723
[1m 704/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2785 - loss: 2.1719
[1m 734/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1715
[1m 760/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2790 - loss: 2.1710
[1m 789/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2793 - loss: 2.1706
[1m 819/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2794 - loss: 2.1704
[1m 846/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2796 - loss: 2.1702
[1m 872/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2797 - loss: 2.1701
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2799 - loss: 2.1700
[1m 926/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2800 - loss: 2.1699
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2801 - loss: 2.1699
[1m 980/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2802 - loss: 2.1698
[1m1009/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2803 - loss: 2.1697
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2804 - loss: 2.1697
[1m1067/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1696
[1m1095/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2805 - loss: 2.1696
[1m1123/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1695
[1m1148/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1695
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2806 - loss: 2.1695 - val_accuracy: 0.3452 - val_loss: 2.0998
Epoch 11/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m25s[0m 22ms/step - accuracy: 0.3125 - loss: 2.4358
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1839  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2901 - loss: 2.1776
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2869 - loss: 2.1802
[1m 107/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1817
[1m 134/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2870 - loss: 2.1833
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2865 - loss: 2.1831
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1819
[1m 212/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1799
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1781
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1765
[1m 287/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1748
[1m 315/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1733
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1719
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1704
[1m 396/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1692
[1m 423/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1682
[1m 452/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1671
[1m 480/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1662
[1m 510/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1652
[1m 536/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2863 - loss: 2.1645
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1638
[1m 591/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2862 - loss: 2.1632
[1m 620/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1627
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2861 - loss: 2.1624
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1620
[1m 705/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1617
[1m 735/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2859 - loss: 2.1614
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1612
[1m 794/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2858 - loss: 2.1609
[1m 823/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1606
[1m 853/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2857 - loss: 2.1603
[1m 884/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1600
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1598
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2855 - loss: 2.1596
[1m 971/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2854 - loss: 2.1595
[1m 999/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1594
[1m1028/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2853 - loss: 2.1592
[1m1057/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1591
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2852 - loss: 2.1590
[1m1116/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1588
[1m1145/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1586
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2851 - loss: 2.1586 - val_accuracy: 0.3528 - val_loss: 2.0682
Epoch 12/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1364
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3233 - loss: 2.0257  
[1m  54/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3210 - loss: 2.0454
[1m  82/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0559
[1m 109/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3125 - loss: 2.0687
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3095 - loss: 2.0749
[1m 163/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3069 - loss: 2.0805
[1m 192/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3048 - loss: 2.0861
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0900
[1m 244/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0925
[1m 272/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0948
[1m 298/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0961
[1m 326/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3005 - loss: 2.0970
[1m 356/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3002 - loss: 2.0978
[1m 381/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2999 - loss: 2.0987
[1m 412/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2994 - loss: 2.0998
[1m 439/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2989 - loss: 2.1010
[1m 466/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2985 - loss: 2.1021
[1m 493/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2981 - loss: 2.1030
[1m 523/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 2.1040
[1m 551/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2973 - loss: 2.1048
[1m 580/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2970 - loss: 2.1057
[1m 605/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2967 - loss: 2.1064
[1m 632/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2964 - loss: 2.1071
[1m 660/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2963 - loss: 2.1076
[1m 689/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2961 - loss: 2.1080
[1m 716/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2959 - loss: 2.1083
[1m 743/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2957 - loss: 2.1088
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2956 - loss: 2.1092
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 2.1096
[1m 826/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2955 - loss: 2.1099
[1m 855/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2953 - loss: 2.1103
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2952 - loss: 2.1107
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2951 - loss: 2.1111
[1m 941/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2950 - loss: 2.1115
[1m 968/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2949 - loss: 2.1118
[1m 997/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2948 - loss: 2.1121
[1m1027/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2947 - loss: 2.1124
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2946 - loss: 2.1127
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2945 - loss: 2.1130
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2944 - loss: 2.1133
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1136
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2943 - loss: 2.1137 - val_accuracy: 0.3381 - val_loss: 2.0821
Epoch 13/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m23s[0m 21ms/step - accuracy: 0.1250 - loss: 2.1654
[1m  29/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2620 - loss: 2.1165  
[1m  58/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2812 - loss: 2.1181
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2841 - loss: 2.1199
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2849 - loss: 2.1220
[1m 142/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2860 - loss: 2.1222
[1m 171/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2869 - loss: 2.1217
[1m 199/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2877 - loss: 2.1218
[1m 228/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2884 - loss: 2.1213
[1m 258/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1207
[1m 286/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1201
[1m 314/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2900 - loss: 2.1196
[1m 343/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2899 - loss: 2.1197
[1m 368/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2897 - loss: 2.1201
[1m 398/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1204
[1m 426/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1206
[1m 457/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1208
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2889 - loss: 2.1210
[1m 514/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1210
[1m 542/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1210
[1m 571/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2888 - loss: 2.1209
[1m 599/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2890 - loss: 2.1207
[1m 628/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2891 - loss: 2.1203
[1m 657/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2892 - loss: 2.1201
[1m 686/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2894 - loss: 2.1198
[1m 714/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2896 - loss: 2.1194
[1m 741/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2898 - loss: 2.1191
[1m 766/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2900 - loss: 2.1188
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2902 - loss: 2.1184
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2904 - loss: 2.1181
[1m 850/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2905 - loss: 2.1178
[1m 878/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2907 - loss: 2.1175
[1m 908/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2909 - loss: 2.1172
[1m 935/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2911 - loss: 2.1169
[1m 962/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2913 - loss: 2.1166
[1m 991/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2914 - loss: 2.1164
[1m1015/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.2916 - loss: 2.1163
[1m1041/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2917 - loss: 2.1161
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.2919 - loss: 2.1159
[1m1098/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2920 - loss: 2.1157
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.2921 - loss: 2.1156
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.2922 - loss: 2.1154 - val_accuracy: 0.3363 - val_loss: 2.0877
Epoch 14/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.2500 - loss: 2.2159
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2508 - loss: 2.1018  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2614 - loss: 2.1008
[1m  79/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2657 - loss: 2.1070
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2691 - loss: 2.1110
[1m 131/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2738 - loss: 2.1109
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2788 - loss: 2.1084
[1m 188/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2826 - loss: 2.1067
[1m 218/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2856 - loss: 2.1045
[1m 245/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2879 - loss: 2.1022
[1m 276/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2901 - loss: 2.0997
[1m 300/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2916 - loss: 2.0974
[1m 328/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2933 - loss: 2.0946
[1m 355/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2946 - loss: 2.0925
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2958 - loss: 2.0910
[1m 407/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2968 - loss: 2.0896
[1m 436/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2977 - loss: 2.0884
[1m 465/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2984 - loss: 2.0874
[1m 495/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2989 - loss: 2.0866
[1m 526/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2993 - loss: 2.0859
[1m 556/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.2997 - loss: 2.0853
[1m 585/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3001 - loss: 2.0849
[1m 616/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3004 - loss: 2.0846
[1m 643/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3006 - loss: 2.0845
[1m 672/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3008 - loss: 2.0842
[1m 699/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3011 - loss: 2.0839
[1m 729/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3014 - loss: 2.0836
[1m 757/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3015 - loss: 2.0835
[1m 786/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3017 - loss: 2.0833
[1m 814/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3019 - loss: 2.0832
[1m 841/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3021 - loss: 2.0830
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3022 - loss: 2.0829
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3023 - loss: 2.0828
[1m 924/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3024 - loss: 2.0827
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3025 - loss: 2.0826
[1m 981/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3026 - loss: 2.0826
[1m1008/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3027 - loss: 2.0825
[1m1035/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3028 - loss: 2.0824
[1m1064/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3029 - loss: 2.0824
[1m1091/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0824
[1m1118/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3030 - loss: 2.0824
[1m1146/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3031 - loss: 2.0824
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3032 - loss: 2.0824 - val_accuracy: 0.3496 - val_loss: 2.0661
Epoch 15/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m26s[0m 23ms/step - accuracy: 0.3125 - loss: 2.1995
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.2966 - loss: 2.1461  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3030 - loss: 2.1233
[1m  84/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3081 - loss: 2.1067
[1m 110/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3109 - loss: 2.0967
[1m 135/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3133 - loss: 2.0899
[1m 160/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3144 - loss: 2.0854
[1m 185/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0838
[1m 210/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3145 - loss: 2.0825
[1m 238/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0821
[1m 266/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3143 - loss: 2.0817
[1m 294/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3142 - loss: 2.0813
[1m 321/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3141 - loss: 2.0809
[1m 347/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3139 - loss: 2.0807
[1m 376/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3138 - loss: 2.0805
[1m 405/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3136 - loss: 2.0802
[1m 431/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3134 - loss: 2.0801
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0799
[1m 484/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3129 - loss: 2.0798
[1m 511/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3128 - loss: 2.0796
[1m 537/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3126 - loss: 2.0793
[1m 567/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3124 - loss: 2.0792
[1m 594/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3123 - loss: 2.0792
[1m 623/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0791
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0789
[1m 678/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3122 - loss: 2.0787
[1m 706/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0785
[1m 736/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3121 - loss: 2.0784
[1m 765/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0782
[1m 793/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3120 - loss: 2.0779
[1m 822/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0778
[1m 845/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0776
[1m 870/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0775
[1m 900/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0774
[1m 927/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0773
[1m 953/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0772
[1m 982/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0771
[1m1010/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3119 - loss: 2.0771
[1m1038/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0770
[1m1069/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0770
[1m1097/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3118 - loss: 2.0770
[1m1126/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0771
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3117 - loss: 2.0770 - val_accuracy: 0.3427 - val_loss: 2.0979
Epoch 16/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.3125 - loss: 2.1445
[1m  24/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3193 - loss: 2.0584  
[1m  51/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3113 - loss: 2.0543
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3107 - loss: 2.0557
[1m 106/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3132 - loss: 2.0559
[1m 132/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3148 - loss: 2.0547
[1m 159/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3150 - loss: 2.0549
[1m 182/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3149 - loss: 2.0552
[1m 209/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3153 - loss: 2.0548
[1m 235/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3158 - loss: 2.0539
[1m 262/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3161 - loss: 2.0533
[1m 290/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3163 - loss: 2.0526
[1m 317/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3165 - loss: 2.0521
[1m 341/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0516
[1m 370/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0513
[1m 397/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0513
[1m 427/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0516
[1m 455/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0520
[1m 485/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0524
[1m 509/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0526
[1m 539/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0527
[1m 566/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0527
[1m 592/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0525
[1m 619/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0523
[1m 648/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0521
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0518
[1m 702/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0517
[1m 730/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0517
[1m 753/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0517
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3172 - loss: 2.0517
[1m 811/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0519
[1m 839/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3171 - loss: 2.0521
[1m 868/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3170 - loss: 2.0523
[1m 896/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0525
[1m 921/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3169 - loss: 2.0526
[1m 946/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0527
[1m 976/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0529
[1m1005/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3168 - loss: 2.0530
[1m1034/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0532
[1m1060/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0533
[1m1087/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0533
[1m1115/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0534
[1m1144/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0534
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3167 - loss: 2.0534 - val_accuracy: 0.3538 - val_loss: 2.0887
Epoch 17/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 2.5822
[1m  26/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3269 - loss: 1.9812  
[1m  52/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3262 - loss: 1.9879
[1m  77/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3289 - loss: 2.0002
[1m 105/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0054
[1m 133/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3326 - loss: 2.0060
[1m 161/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 2.0065
[1m 187/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3327 - loss: 2.0087
[1m 215/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3328 - loss: 2.0099
[1m 239/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3330 - loss: 2.0104
[1m 269/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3331 - loss: 2.0108
[1m 297/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 2.0111
[1m 323/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3326 - loss: 2.0118
[1m 352/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3324 - loss: 2.0125
[1m 380/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3322 - loss: 2.0134
[1m 404/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 2.0143
[1m 429/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3318 - loss: 2.0154
[1m 458/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3316 - loss: 2.0164
[1m 486/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3314 - loss: 2.0173
[1m 512/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3311 - loss: 2.0180
[1m 538/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3309 - loss: 2.0189
[1m 564/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 2.0198
[1m 590/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3303 - loss: 2.0208
[1m 617/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3300 - loss: 2.0216
[1m 646/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3297 - loss: 2.0224
[1m 673/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3294 - loss: 2.0231
[1m 700/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3292 - loss: 2.0238
[1m 728/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3290 - loss: 2.0244
[1m 755/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3289 - loss: 2.0249
[1m 782/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3288 - loss: 2.0253
[1m 806/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3288 - loss: 2.0255
[1m 834/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3287 - loss: 2.0257
[1m 861/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3287 - loss: 2.0259
[1m 889/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3286 - loss: 2.0262
[1m 917/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3284 - loss: 2.0265
[1m 944/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3283 - loss: 2.0268
[1m 973/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3282 - loss: 2.0271
[1m1000/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 2.0273
[1m1029/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3278 - loss: 2.0276
[1m1055/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0278
[1m1084/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0280
[1m1111/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0282
[1m1139/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0285
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3272 - loss: 2.0286 - val_accuracy: 0.3570 - val_loss: 2.1055
Epoch 18/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 22ms/step - accuracy: 0.1875 - loss: 2.3667
[1m  27/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3186 - loss: 2.0645  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3207 - loss: 2.0406
[1m  86/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3254 - loss: 2.0316
[1m 112/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0296
[1m 140/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0315
[1m 164/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3278 - loss: 2.0325
[1m 191/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 2.0321
[1m 219/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3284 - loss: 2.0317
[1m 249/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3283 - loss: 2.0320
[1m 280/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3281 - loss: 2.0319
[1m 305/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3279 - loss: 2.0322
[1m 334/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3277 - loss: 2.0330
[1m 361/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0338
[1m 386/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0342
[1m 414/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0345
[1m 442/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0343
[1m 470/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3267 - loss: 2.0338
[1m 497/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3268 - loss: 2.0331
[1m 521/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3270 - loss: 2.0325
[1m 547/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3271 - loss: 2.0319
[1m 572/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3272 - loss: 2.0315
[1m 601/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3272 - loss: 2.0311
[1m 627/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0307
[1m 652/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3273 - loss: 2.0303
[1m 681/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0298
[1m 711/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3274 - loss: 2.0292
[1m 740/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0288
[1m 770/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0285
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0283
[1m 825/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0282
[1m 854/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0279
[1m 883/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0277
[1m 912/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0274
[1m 937/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0272
[1m 964/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0270
[1m 992/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0268
[1m1021/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 2.0266
[1m1050/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0264
[1m1078/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0262
[1m1107/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0260
[1m1135/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0258
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3275 - loss: 2.0257 - val_accuracy: 0.3534 - val_loss: 2.1145
Epoch 19/27

[1m   1/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m24s[0m 21ms/step - accuracy: 0.1875 - loss: 1.9340
[1m  28/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3515 - loss: 1.9441  
[1m  56/1155[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 2ms/step - accuracy: 0.3603 - loss: 1.9355
[1m  85/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3575 - loss: 1.9423
[1m 114/1155[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3522 - loss: 1.9518
[1m 141/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3477 - loss: 1.9584
[1m 168/1155[0m [32m━━[0m[37m━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3441 - loss: 1.9646
[1m 197/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3407 - loss: 1.9701
[1m 226/1155[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3387 - loss: 1.9728
[1m 254/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3369 - loss: 1.9752
[1m 282/1155[0m [32m━━━━[0m[37m━━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3352 - loss: 1.9780
[1m 309/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3339 - loss: 1.9805
[1m 336/1155[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3329 - loss: 1.9823
[1m 363/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3320 - loss: 1.9841
[1m 389/1155[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3313 - loss: 1.9853
[1m 415/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3306 - loss: 1.9865
[1m 443/1155[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3301 - loss: 1.9876
[1m 471/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3296 - loss: 1.9886
[1m 499/1155[0m [32m━━━━━━━━[0m[37m━━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3292 - loss: 1.9893
[1m 527/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3290 - loss: 1.9898
[1m 552/1155[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3287 - loss: 1.9902
[1m 581/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3285 - loss: 1.9907
[1m 607/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m1s[0m 2ms/step - accuracy: 0.3284 - loss: 1.9910
[1m 635/1155[0m [32m━━━━━━━━━━[0m[37m━━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3283 - loss: 1.9913
[1m 662/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3282 - loss: 1.9915
[1m 688/1155[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3281 - loss: 1.9917
[1m 713/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 1.9918
[1m 742/1155[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3280 - loss: 1.9921
[1m 771/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3279 - loss: 1.9923
[1m 798/1155[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3279 - loss: 1.9925
[1m 821/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3279 - loss: 1.9926
[1m 849/1155[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3279 - loss: 1.9928
[1m 875/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3279 - loss: 1.9930
[1m 901/1155[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3279 - loss: 1.9931
[1m 930/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3278 - loss: 1.9933
[1m 960/1155[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3278 - loss: 1.9934
[1m 986/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3278 - loss: 1.9936
[1m1016/1155[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 1.9937
[1m1043/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3277 - loss: 1.9940
[1m1072/1155[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 1.9942
[1m1101/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 1.9945
[1m1131/1155[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 2ms/step - accuracy: 0.3276 - loss: 1.9947
[1m1155/1155[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m3s[0m 2ms/step - accuracy: 0.3276 - loss: 1.9948 - val_accuracy: 0.3564 - val_loss: 2.1086

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m54s[0m 644ms/step
[1m48/86[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 1ms/step   
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 8ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 9ms/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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:05[0m 841ms/step
[1m 54/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 957us/step  
[1m102/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 1ms/step  
[1m160/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 955us/step
[1m221/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 921us/step
[1m275/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 925us/step
[1m327/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 931us/step
[1m379/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 936us/step
[1m432/578[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 939us/step
[1m486/578[0m [32m━━━━━━━━━━━━━━━━[0m[37m━━━━[0m [1m0s[0m 938us/step
[1m539/578[0m [32m━━━━━━━━━━━━━━━━━━[0m[37m━━[0m [1m0s[0m 940us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/step

[1m 1/86[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m1s[0m 17ms/step
[1m53/86[0m [32m━━━━━━━━━━━━[0m[37m━━━━━━━━[0m [1m0s[0m 963us/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 7ms/step  
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 56/158[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 919us/step
[1m114/158[0m [32m━━━━━━━━━━━━━━[0m[37m━━━━━━[0m [1m0s[0m 891us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 33.39 [%]
Global F1 score (validation) = 32.13 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.03860931 0.0293276  0.02600554 ... 0.04105038 0.05181223 0.01901202]
 [0.0008506  0.00176076 0.00181419 ... 0.16382323 0.00445321 0.0028411 ]
 [0.00551244 0.00402109 0.00221067 ... 0.01128571 0.00192014 0.00493931]
 ...
 [0.16200988 0.05949024 0.17098758 ... 0.00639702 0.16001235 0.13041681]
 [0.18008468 0.06065404 0.10402701 ... 0.01708719 0.10152936 0.0773311 ]
 [0.15817055 0.06236106 0.18795574 ... 0.00985615 0.14181527 0.0845213 ]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 38.65 [%]
Global accuracy score (test) = 27.77 [%]
Global F1 score (train) = 37.98 [%]
Global F1 score (test) = 26.89 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.26      0.46      0.33       184
 CAMINAR CON MÓVIL O LIBRO       0.28      0.27      0.28       184
       CAMINAR USUAL SPEED       0.21      0.08      0.11       184
            CAMINAR ZIGZAG       0.23      0.36      0.28       184
          DE PIE BARRIENDO       0.42      0.26      0.32       184
   DE PIE DOBLANDO TOALLAS       0.34      0.33      0.34       184
    DE PIE MOVIENDO LIBROS       0.21      0.21      0.21       184
          DE PIE USANDO PC       0.06      0.06      0.06       184
        FASE REPOSO CON K5       0.40      0.63      0.49       184
INCREMENTAL CICLOERGOMETRO       0.52      0.37      0.43       184
           SENTADO LEYENDO       0.19      0.14      0.16       184
         SENTADO USANDO PC       0.12      0.06      0.08       184
      SENTADO VIENDO LA TV       0.15      0.23      0.18       184
   SUBIR Y BAJAR ESCALERAS       0.34      0.21      0.26       184
                    TROTAR       0.49      0.53      0.51       161

                  accuracy                           0.28      2737
                 macro avg       0.28      0.28      0.27      2737
              weighted avg       0.28      0.28      0.27      2737


Accuracy capturado en la ejecución 29: 27.77 [%]
F1-score capturado en la ejecución 29: 26.89 [%]

=== 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, 3, 250)
(18469, 3, 250)

[1m  1/578[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m8:01[0m 834ms/step
[1m 54/578[0m [32m━[0m[37m━━━━━━━━━━━━━━━━━━━[0m [1m0s[0m 956us/step  
[1m113/578[0m [32m━━━[0m[37m━━━━━━━━━━━━━━━━━[0m [1m0s[0m 903us/step
[1m173/578[0m [32m━━━━━[0m[37m━━━━━━━━━━━━━━━[0m [1m0s[0m 883us/step
[1m225/578[0m [32m━━━━━━━[0m[37m━━━━━━━━━━━━━[0m [1m0s[0m 905us/step
[1m280/578[0m [32m━━━━━━━━━[0m[37m━━━━━━━━━━━[0m [1m0s[0m 906us/step
[1m338/578[0m [32m━━━━━━━━━━━[0m[37m━━━━━━━━━[0m [1m0s[0m 900us/step
[1m394/578[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 900us/step
[1m451/578[0m [32m━━━━━━━━━━━━━━━[0m[37m━━━━━[0m [1m0s[0m 898us/step
[1m505/578[0m [32m━━━━━━━━━━━━━━━━━[0m[37m━━━[0m [1m0s[0m 902us/step
[1m560/578[0m [32m━━━━━━━━━━━━━━━━━━━[0m[37m━[0m [1m0s[0m 903us/step
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 2ms/step  
[1m578/578[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m2s[0m 2ms/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 7ms/step
[1m86/86[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 7ms/step

[1m  1/158[0m [37m━━━━━━━━━━━━━━━━━━━━[0m [1m2s[0m 16ms/step
[1m 53/158[0m [32m━━━━━━[0m[37m━━━━━━━━━━━━━━[0m [1m0s[0m 977us/step
[1m109/158[0m [32m━━━━━━━━━━━━━[0m[37m━━━━━━━[0m [1m0s[0m 936us/step
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 4ms/step  
[1m158/158[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m1s[0m 4ms/step
Global accuracy score (validation) = 35.64 [%]
Global F1 score (validation) = 34.15 [%]
[[8.]
 [8.]
 [8.]
 ...
 [3.]
 [3.]
 [3.]]
(2737, 1)
[[0.00987193 0.0110641  0.01256367 ... 0.02650611 0.03279934 0.00829332]
 [0.00286113 0.00274993 0.00178672 ... 0.062821   0.01392553 0.00487573]
 [0.00045925 0.00084995 0.00107683 ... 0.00430503 0.00283951 0.00128936]
 ...
 [0.19092838 0.03528372 0.17747088 ... 0.00445791 0.13666947 0.13021784]
 [0.23049873 0.04039238 0.13095015 ... 0.01489944 0.09175381 0.1023971 ]
 [0.16974092 0.05865273 0.15065941 ... 0.0101316  0.16914396 0.07541749]]
(2737, 15)
-------------------------------------------------

Global accuracy score (train) = 39.47 [%]
Global accuracy score (test) = 29.01 [%]
Global F1 score (train) = 38.74 [%]
Global F1 score (test) = 27.88 [%]
                            precision    recall  f1-score   support

     CAMINAR CON LA COMPRA       0.25      0.46      0.32       184
 CAMINAR CON MÓVIL O LIBRO       0.23      0.22      0.23       184
       CAMINAR USUAL SPEED       0.10      0.04      0.06       184
            CAMINAR ZIGZAG       0.27      0.42      0.33       184
          DE PIE BARRIENDO       0.45      0.24      0.31       184
   DE PIE DOBLANDO TOALLAS       0.28      0.30      0.29       184
    DE PIE MOVIENDO LIBROS       0.19      0.12      0.15       184
          DE PIE USANDO PC       0.15      0.09      0.11       184
        FASE REPOSO CON K5       0.30      0.75      0.43       184
INCREMENTAL CICLOERGOMETRO       0.67      0.36      0.47       184
           SENTADO LEYENDO       0.22      0.15      0.18       184
         SENTADO USANDO PC       0.34      0.18      0.24       184
      SENTADO VIENDO LA TV       0.15      0.21      0.18       184
   SUBIR Y BAJAR ESCALERAS       0.41      0.30      0.35       184
                    TROTAR       0.57      0.53      0.55       161

                  accuracy                           0.29      2737
                 macro avg       0.31      0.29      0.28      2737
              weighted avg       0.30      0.29      0.28      2737


Accuracy capturado en la ejecución 30: 29.01 [%]
F1-score capturado en la ejecución 30: 27.88 [%]

=== RESUMEN FINAL ===
Accuracies: [27.22, 29.08, 28.13, 26.93, 31.35, 27.77, 27.66, 29.12, 27.26, 26.34, 28.02, 27.84, 29.45, 29.81, 28.32, 28.21, 27.15, 30.14, 29.92, 29.27, 26.89, 29.23, 28.5, 28.1, 30.03, 26.31, 29.19, 28.32, 27.77, 29.01]
F1-scores: [27.12, 28.65, 27.95, 26.27, 30.13, 25.67, 26.8, 27.58, 26.17, 25.8, 26.76, 26.85, 29.43, 29.75, 26.97, 26.9, 26.04, 29.71, 30.31, 27.69, 24.85, 27.8, 28.18, 27.1, 28.87, 25.23, 27.32, 28.04, 26.89, 27.88]
Accuracy mean: 28.4113 | std: 1.1907
F1 mean: 27.4903 | std: 1.4089

Resultados guardados en /mnt/nvme1n2/git/uniovi-simur-wearablepermed-data/output/Paper_results/cases_dataset_M/case_M_CAPTURE24_acc_17_classes/metrics_test.npz
